Publications
Full list also on Google Scholar. Tengfei Ma in bold; * equal contribution; † corresponding author.
2026
- EMNLP 2026 FindingsGuided Permutation Scoring (GPS): Option-Order Permutation for Multiple-Choice Question Answering
The 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP) Findings, 2026. - SDM 2026SC-JEPA: Stabilizing Latent Predictive Learning for Time-Series Anomaly Prediction
SIAM International Conference on Data Mining (SDM), 2026. (Previously named MTS-JEPA; a preliminary version is also accepted at the ICML 2026 AI Forecasting workshop.) - ECML PKDD 2026Tensor-TimesFM: High-Dimensional Sparse Time Series Forecasting with Tensor Decoders and Latent Dynamics Prediction
Joint European Conference on Machine Learning and Knowledge Discovery in Databases, 2026. - MICCAI 2026Spatiotemporal Modeling of Tumor Dynamics via Optimal Transport for Enhanced Longitudinal Analysis
The 29th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), 2026. - ACM BCB 2026Efficient Imputation for Patch-based Tabular Missing Data via Cluster-regularized Optimal Transport
The 17th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics (ACM BCB), 2026. - KDD 2026Domain-Specific Data Synthesis for LLMs through Minimal Sufficient Representation Learning
The 32nd SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2026. - KDD 2026CAAD: Causality-Aware Multivariate Time Series Anomaly Detection via Multi-Scale Alignment and Structural Causal Consistency
The 32nd SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2026. - ICML 2026Resting Neurons, Active Insights: Robustify Activation Sparsity for Large Language Models
The 43rd International Conference on Machine Learning (ICML), 2026. - ACL 2026 FindingsHypEHR: Hyperbolic Modeling of Electronic Health Records for Efficient Question Answering
The 64th Annual Meeting of the Association for Computational Linguistics (ACL) Findings, 2026. - TMLR 2026Graph Concept Bottleneck Models
Transactions on Machine Learning Research (TMLR), 2026. - AMIA 2026A Novel Approach to Zero-Shot Drug-Drug Interaction Prediction Enabled by EHR-Augmented Knowledge Graphs
AMIA 2026 Amplify Informatics Conference, 2026. (Poster) - ICLR 2026A Problem-Oriented Perspective and Anchor Verification for Code Optimization
The Fourteenth International Conference on Learning Representations (ICLR), 2026.
2025
- TMLR 2025Self-Supervised Learning on Molecular Graphs: A Systematic Investigation of Masking Design
Transactions on Machine Learning Research (TMLR), 2025. - LoG 2025When Structure Doesn't Help: LLMs Do Not Read Text-Attributed Graphs as Effectively as We Expected
Learning on Graphs Conference (LoG), 2025. - ML4H 2025Concept-Enhanced Automatic ICD Coding using Large Language Models
The AHLI Machine Learning for Health (ML4H) Symposium Proceedings, 2025. - ML4H 2025 FindingsDual-Pathway Fusion of EHRs and Knowledge Graphs for Predicting Unseen Drug-Drug Interactions
The AHLI Machine Learning for Health (ML4H) Symposium Findings Track, 2025. - Sci. Rep. 2025Integrated machine learning analysis of proteomic and transcriptomic data identifies healing associated targets in diabetic wound repair
Scientific Reports, 2025. (* Equal contribution; † Corresponding) - UIST 2025MACEDON: Supporting Programmers with Real-Time Multi-Dimensional Code Evaluation and Optimization
Proceedings of the 38th Annual ACM Symposium on User Interface Software and Technology (UIST), 2025. - ACL 2025 FindingsNBDESCRIB: A Dataset for Text Description Generation from Tables and Code in Jupyter Notebooks with Guidelines
The 63rd Annual Meeting of the Association for Computational Linguistics (ACL) Findings, 2025. - KDD 2025Understanding and Tackling Over-Dilution in Graph Neural Networks
ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), 2025. - TPAMI 2025Wasserstein Graph Neural Networks for Graphs with Missing Attributes
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2025. - ICLR 2025Shedding Light on Time Series Classification using Interpretability Gated Networks
The Thirteenth International Conference on Learning Representations (ICLR), 2025. († Corresponding) - CHI 2025Influencer: Empowering Everyday Users in Creating Promotional Posts via AI-infused Exploration and Customization
The ACM CHI Conference on Human Factors in Computing Systems (CHI), 2025. - JMLR 2025Enhancing Graph Representation Learning with Local Persistent Homology Features
Journal of Machine Learning Research (JMLR), 2025. - BSPC 2025Quantitative ultrasound augmented with machine learning to assess tissue microstructure during wound healing
Biomedical Signal Processing and Control, Volume 103, 2025. - AAAI 2025Uncovering LLM-Generated Code: A Zero-Shot Synthetic Code Detector via Code Rewriting
The Thirty-Ninth AAAI Conference on Artificial Intelligence (AAAI), 2025. (* Equal contribution)
2024
- NeurIPS 2024Abstracted Shapes as Tokens - A Generalizable and Interpretable Model for Time-series
The Thirty-eighth Annual Conference on Neural Information Processing Systems (NeurIPS), 2024. († Corresponding) - EMNLP 2024FAC2E: Better Understanding Large Language Model Capabilities by Dissociating Language and Cognition
The 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2024. - ECCV 2024TrojVLM: Backdoor Attack Against Vision Language Models
European Conference on Computer Vision (ECCV), 2024. - ICML 2024What Improves the Generalization of Graph Transformer? A Theoretical Dive into Self-attention and Positional Encoding
The Forty-first International Conference on Machine Learning (ICML), 2024. - NAACL 2024 FindingsTram: A Token-level Retrieval-augmented Mechanism for Source Code Summarization
Findings of the North American Chapter of the Association for Computational Linguistics (NAACL Findings), 2024. - AAAI 2024AdaCCD: Adaptive Semantic Contrasts Discovery based Cross Lingual Adaptation for Code Clone Detection
The Thirty-Eighth AAAI Conference on Artificial Intelligence (AAAI), 2024.
2023
- LoG 2023 OralCycle Invariant Positional Encoding for Graph Representation Learning
The Second Learning on Graphs Conference (LoG), 2023. - EMNLP 2023Knowledge Graph Compression Enhances Diverse Commonsense Generation
The 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2023. - EMNLP 2023CP-BCS: Binary Code Summarization Guided by Control Flow Graph and Pseudo Code
The 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2023. - NeurIPS 2023SyncTREE: Fast Timing Analysis for Integrated Circuit Design through a Physics-informed Tree-based Graph Neural Network
Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS), 2023. - Adv. Healthc. Mater. 2023A Miniaturized, Battery-free, Wireless Wound Monitor that Predicts Wound Closure Rate Early
Advanced Healthcare Materials, 2023. (* Equal contribution) - KDD 2023 ADSIGB: Addressing The Gaps In Labeling, Features, Heterogeneity, and Size of Public Graph Datasets for Deep Learning Research
ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), Applied Data Science Track, 2023. - UAI 2023Federated Learning of Models Pre-Trained on Different Features with Consensus Graphs
The 39th Conference on Uncertainty in Artificial Intelligence (UAI), 2023. - CHI 2023Slide4N: Creating Presentation Slides from Computational Notebooks with Human-AI Collaboration
The ACM CHI Conference on Human Factors in Computing Systems (CHI), 2023. - ICLR 2023Weighted Clock Logic Point Process
The Eleventh International Conference on Learning Representations (ICLR), 2023.
2022
- LoG 2022 SpotlightAn Analysis of Virtual Nodes in Graph Neural Networks for Link Prediction (Extended Abstract)
The First Learning on Graphs Conference (LoG), 2022. - NeurIPS 2022 WorkshopRetrosynthesis Prediction Revisited
NeurIPS 2022 Workshop on AI for Science (AI4Science), 2022. - NeurIPS 2022Neural Approximation of Extended Persistent Homology on Graphs
Thirty-sixth Conference on Neural Information Processing Systems (NeurIPS), 2022. - ICDM 2022Neuro-symbolic Models for Interpretable Time Series Classification using Temporal Logic Description
The 22nd IEEE International Conference on Data Mining (ICDM), 2022. - Anal. Appl. 2022BiGCN: A Bi-directional Low-Pass Filtering Graph Neural Network
Analysis and Applications (special issue of AA 20th Anniversary), 2022. - ICML 2022Cycle Representation Learning for Inductive Relation Prediction
The 39th International Conference on Machine Learning (ICML), 2022. - NAACL 2022A Study of the Attention Abnormality in Trojaned BERTs
The 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT), 2022. - TVCG 2022GNNLens: A Visual Analytics Approach for Prediction Error Diagnosis of Graph Neural Networks
IEEE Transactions on Visualization and Computer Graphics (TVCG), 2022. - INFOCOM 2022MalGraph: Hierarchical Graph Neural Networks for Robust Windows Malware Detection
IEEE International Conference on Computer Communications (INFOCOM), 2022. - TKDE 2022CHEER: Rich Model Helps Poor Model via Knowledge Infusion
IEEE Transactions on Knowledge and Data Engineering (TKDE), 2022. - arXiv 2022When does a spectral graph neural network fail in node classification?
arXiv preprint arXiv:2202.07902, 2022. - arXiv 2022Improving long tailed document-level relation extraction via easy relation augmentation and contrastive learning
arXiv preprint arXiv:2205.10511, 2022.
2021
- EMNLP 2021Timeline Summarization based on Event Graph Compression via Time-Aware Optimal Transport
The 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2021. - EMNLP 2021 FindingsConstructing contrastive samples via summarization for text classification with limited annotations
Findings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP Findings), 2021. - ISWC 2021 Best Paper Award (Research Track)Improving Inductive Link Prediction Using Hyper-Relational Facts
The 20th International Semantic Web Conference (ISWC), 2021. - ICML 2021Link Prediction with Persistence Homology: An Interactive View
The Thirty-eighth International Conference on Machine Learning (ICML), 2021. - TKDD 2021Exploiting Heterogeneous Graph Neural Networks with Latent Worker/Task Correlation Information for Label Aggregation in Crowdsourcing
ACM Transactions on Knowledge Discovery from Data (TKDD), 2021. - AAAI 2021Unsupervised Learning of Graph Hierarchical Abstractions with Differentiable Coarsening and Optimal Transport
The Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI), 2021. (* Equal contribution) - TNNLS 2021Hierarchical Graph Matching Networks for Deep Graph Similarity Learning
IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2021. - TKDD 2021Deep Graph Matching and Searching for Semantic Code Retrieval
ACM Transactions on Knowledge Discovery from Data (TKDD), 2021. - Book 2021图神经网络：基础与前沿 (Graph Neural Networks: Fundamentals and Frontiers)
电子工业出版社 (Publishing House of Electronics Industry), 2021.
2020
- IEEE BigData 2020Supervised Topic Compositional Neural Language Model for Clinical Narrative Understanding
IEEE International Conference on Big Data (BigData), 2020. - EMNLP 2020Unsupervised Reference-Free Summary Quality Evaluation via Contrastive Learning
The 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2020. (* Equal contribution) - ICML 2020 WorkshopRelation-Dependent Sampling for Multi-Relational Link Prediction
Graph Representation Learning and Beyond (GRL+) Workshop at ICML 2020, 2020. (* Equal contribution) - EML 2020Artificial intelligence method to design and fold alpha-helix structural proteins from the primary amino acid sequence
Extreme Mechanics Letters, 2020. (* Equal contribution) - ICLR 2020Curvature Graph Network
The Eighth International Conference on Learning Representations (ICLR), 2020. - AAAI 2020EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs
The Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI), 2020. (* Equal contribution) - AAAI 2020 OralOnline Planner Selection with Graph Neural Networks and Adaptive Scheduling
The Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI), 2020. - AAAI 2020 TutorialGraph Neural Networks: Models and Applications
Tutorial at the Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI), 2020. - KDD 2020 TutorialDeep Graph Learning: Foundations, Advances and Applications
Tutorial at the ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2020.
2019
- NeurIPS 2019 WorkshopLearning Logical Representations from Natural Languages with Weak Supervision and Back Translation
NeurIPS 2019 Workshop on Knowledge Representation & Reasoning Meets Machine Learning (KR2ML), 2019. - EMNLP 2019Pre-Training BERT on Domain Resources for Short Answer Grading
Conference on Empirical Methods in Natural Language Processing and International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), 2019. - EMNLP 2019 WorkshopGraph Enhanced Cross-Domain Text-to-SQL Generation
EMNLP 2019 Workshop on Graph-Based Methods for NLP (TextGraphs), 2019. - TVCG/InfoVis 2019DeepDrawing: A Deep Learning Approach to Graph Drawing
IEEE Transactions on Visualization and Computer Graphics (Proceedings of InfoVis), 2019. - ACM BCB 2019PEARL: Prototype Learning via Rule Learning
ACM Conference on Bioinformatics, Computational Biology, and Health Informatics (ACM BCB), 2019. (* Equal contribution) - ICML 2019 WorkshopIPC: A Benchmark Data Set for Learning with Graph-Structured Data
ICML 2019 Workshop on Learning and Reasoning with Graph-Structured Data, 2019. - IJCAI 2019Pre-training of Graph Augmented Transformers for Medication Recommendation
The 28th International Joint Conference on Artificial Intelligence (IJCAI), 2019. - IJCAI 2019RDPD: Rich Data Helps Poor Data via Imitation
The 28th International Joint Conference on Artificial Intelligence (IJCAI), 2019. - IJCAI 2019MINA: Multilevel Knowledge-Guided Attention for Modeling Electrocardiography Signals
The 28th International Joint Conference on Artificial Intelligence (IJCAI), 2019. - DSN 2019Reaching Data Confidentiality and Model Accountability on the CalTrain
The 49th IEEE/IFIP International Conference on Dependable Systems and Networks (DSN), 2019. - AAAI 2019GAMENet: Graph Augmented MEmory Networks for Recommending Medication Combination
The Thirty-Third AAAI Conference on Artificial Intelligence (AAAI), 2019. - arXiv 2019GENN: Predicting Correlated Drug-drug Interactions with Graph Energy Neural Networks
arXiv preprint arXiv:1910.02107, 2019.
2018
- NeurIPS 2018 WorkshopScalable Graph Learning for Anti-Money Laundering: A First Look
NeurIPS 2018 Workshop on Challenges and Opportunities for AI in Financial Services: the Impact of Fairness, Explainability, Accuracy, and Privacy (FEAP-AI4Fin), 2018. - NeurIPS 2018Constrained Generation of Semantically Valid Graphs via Regularizing Variational Autoencoders
Neural Information Processing Systems (NeurIPS), 2018. (* Equal contribution) - IJCAI-ECAI 2018Drug Similarity Integration Through Attentive Multi-view Graph Auto-Encoders
The 27th International Joint Conference on Artificial Intelligence and the 23rd European Conference on Artificial Intelligence (IJCAI-ECAI), 2018. - AIED 2018Preliminary Evaluations of a Dialogue-based Tutor
The 19th International Conference on Artificial Intelligence in Education (AIED), 2018. - ICLS 2018Dialogue-based tutoring at scale: Design and Challenges
The 13th International Conference of the Learning Sciences (ICLS), 2018. - ICLR 2018FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling
The Sixth International Conference on Learning Representations (ICLR), 2018. (* Equal contribution) - PLOS ONE 2018Readmission Prediction via Deep Contextual Embedding of Clinical Concepts
PLOS ONE, 2018. (* Equal contribution) - SDM 2018Health-ATM: A Deep Architecture for Multifaceted Patient Health Record Representation and Risk Prediction
SIAM International Conference on Data Mining (SDM), 2018. (* Equal contribution) - WWW 2018Human-level multiple choice question guessing without domain knowledge: Machine-learning of framing effects
The Web Conference (WWW), Cognitive Computing Track, 2018. - Book Chapter 2018Wizard's Apprentice Powers Testing of Advanced Conversational Intelligent Tutors
Tutoring and Intelligent Tutoring Systems, Chapter 12, Nova Science Pub Inc, 2018. - arXiv 2018AWE: Asymmetric Word Embedding for Textual Entailment
arXiv preprint arXiv:1809.04047, 2018.
2017
- IJCAI 2017Inverted Bilingual Topic Models for Lexicon Extraction from Non-parallel Data
Proceedings of the 26th International Joint Conference on Artificial Intelligence (IJCAI), Melbourne, Australia, 2017. - AIED 2017Wizard's Apprentice: Cognitive Suggestion Support for Wizard-of-Oz Question Answering
The 18th International Conference on Artificial Intelligence in Education (AIED), Wuhan, China, 2017. - EACL 2017Multilingual Training of Crosslingual Word Embeddings
Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics (EACL), Valencia, Spain, 2017.
2016
- EMNLP 2016Learning Crosslingual Word Embeddings without Bilingual Corpora
Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing (EMNLP), Austin, Texas, USA, pp. 1285–1295, 2016.
2015 and before
- AAAI 2015The Hybrid Nested/Hierarchical Dirichlet Process and its Application to Topic Modeling with Word Differentiation
The Twenty-Ninth AAAI Conference on Artificial Intelligence (AAAI-15), Austin, USA, pp. 2835–2841, 2015. - EMNLP 2013Automatically Determining a Proper Length for Multi-document Summarization: A Bayesian Nonparametric Approach
The 2013 Conference on Empirical Methods in Natural Language Processing (EMNLP), Seattle, USA, pp. 736–749, 2013. - SCIA 2013Automated Tracing of Retinal Blood Vessels Using Graphical Models
Scandinavian Conference on Image Analysis (SCIA), pp. 277–289, 2013. - IJCNLP 2011Named Entity Recognition in Chinese News Comments on the Web
The 5th International Joint Conference on Natural Language Processing (IJCNLP), pp. 856–864, 2011. - ICDM 2010Multi-Document Summarization Using Minimum Distortion
Proceedings of the 10th IEEE International Conference on Data Mining (ICDM), Sydney, pp. 354–363, 2010. - TAC 2010PKUTM participation at TAC 2010 RTE and summarization track
Proceedings of Text Analysis Conference (TAC), 2010. - COLING 2010Opinion Target Extraction in Chinese News Comments
Proceedings of the 23rd International Conference on Computational Linguistics (COLING), Beijing, pp. 782–790, 2010. - NTCIR-8 2010 OralPKUTM Experiments in NTCIR8 MOAT Task
NTCIR-8, Tokyo, pp. 228–233, 2010. (Oral; * Equal contribution)
Graph Neural Networks
Scalable and dynamic graph learning, graph foundation models, and learning with geometry and topology.
- TMLR 2026Graph Concept Bottleneck Models
Transactions on Machine Learning Research (TMLR), 2026. - AMIA 2026A Novel Approach to Zero-Shot Drug-Drug Interaction Prediction Enabled by EHR-Augmented Knowledge Graphs
AMIA 2026 Amplify Informatics Conference, 2026. (Poster) - TMLR 2025Self-Supervised Learning on Molecular Graphs: A Systematic Investigation of Masking Design
Transactions on Machine Learning Research (TMLR), 2025. - LoG 2025When Structure Doesn't Help: LLMs Do Not Read Text-Attributed Graphs as Effectively as We Expected
Learning on Graphs Conference (LoG), 2025. - ML4H 2025 FindingsDual-Pathway Fusion of EHRs and Knowledge Graphs for Predicting Unseen Drug-Drug Interactions
The AHLI Machine Learning for Health (ML4H) Symposium Findings Track, 2025. - KDD 2025Understanding and Tackling Over-Dilution in Graph Neural Networks
ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), 2025. - TPAMI 2025Wasserstein Graph Neural Networks for Graphs with Missing Attributes
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2025. - JMLR 2025Enhancing Graph Representation Learning with Local Persistent Homology Features
Journal of Machine Learning Research (JMLR), 2025. - ICML 2024What Improves the Generalization of Graph Transformer? A Theoretical Dive into Self-attention and Positional Encoding
The Forty-first International Conference on Machine Learning (ICML), 2024. - LoG 2023 OralCycle Invariant Positional Encoding for Graph Representation Learning
The Second Learning on Graphs Conference (LoG), 2023. - EMNLP 2023Knowledge Graph Compression Enhances Diverse Commonsense Generation
The 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2023. - NeurIPS 2023SyncTREE: Fast Timing Analysis for Integrated Circuit Design through a Physics-informed Tree-based Graph Neural Network
Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS), 2023. - KDD 2023 ADSIGB: Addressing The Gaps In Labeling, Features, Heterogeneity, and Size of Public Graph Datasets for Deep Learning Research
ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), Applied Data Science Track, 2023. - UAI 2023Federated Learning of Models Pre-Trained on Different Features with Consensus Graphs
The 39th Conference on Uncertainty in Artificial Intelligence (UAI), 2023. - LoG 2022 SpotlightAn Analysis of Virtual Nodes in Graph Neural Networks for Link Prediction (Extended Abstract)
The First Learning on Graphs Conference (LoG), 2022. - NeurIPS 2022 WorkshopRetrosynthesis Prediction Revisited
NeurIPS 2022 Workshop on AI for Science (AI4Science), 2022. - NeurIPS 2022Neural Approximation of Extended Persistent Homology on Graphs
Thirty-sixth Conference on Neural Information Processing Systems (NeurIPS), 2022. - Anal. Appl. 2022BiGCN: A Bi-directional Low-Pass Filtering Graph Neural Network
Analysis and Applications (special issue of AA 20th Anniversary), 2022. - ICML 2022Cycle Representation Learning for Inductive Relation Prediction
The 39th International Conference on Machine Learning (ICML), 2022. - TVCG 2022GNNLens: A Visual Analytics Approach for Prediction Error Diagnosis of Graph Neural Networks
IEEE Transactions on Visualization and Computer Graphics (TVCG), 2022. - INFOCOM 2022MalGraph: Hierarchical Graph Neural Networks for Robust Windows Malware Detection
IEEE International Conference on Computer Communications (INFOCOM), 2022. - arXiv 2022When does a spectral graph neural network fail in node classification?
arXiv preprint arXiv:2202.07902, 2022. - EMNLP 2021Timeline Summarization based on Event Graph Compression via Time-Aware Optimal Transport
The 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2021. - ISWC 2021 Best Paper Award (Research Track)Improving Inductive Link Prediction Using Hyper-Relational Facts
The 20th International Semantic Web Conference (ISWC), 2021. - ICML 2021Link Prediction with Persistence Homology: An Interactive View
The Thirty-eighth International Conference on Machine Learning (ICML), 2021. - TKDD 2021Exploiting Heterogeneous Graph Neural Networks with Latent Worker/Task Correlation Information for Label Aggregation in Crowdsourcing
ACM Transactions on Knowledge Discovery from Data (TKDD), 2021. - AAAI 2021Unsupervised Learning of Graph Hierarchical Abstractions with Differentiable Coarsening and Optimal Transport
The Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI), 2021. (* Equal contribution) - TNNLS 2021Hierarchical Graph Matching Networks for Deep Graph Similarity Learning
IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2021. - TKDD 2021Deep Graph Matching and Searching for Semantic Code Retrieval
ACM Transactions on Knowledge Discovery from Data (TKDD), 2021. - Book 2021图神经网络：基础与前沿 (Graph Neural Networks: Fundamentals and Frontiers)
电子工业出版社 (Publishing House of Electronics Industry), 2021. - ICML 2020 WorkshopRelation-Dependent Sampling for Multi-Relational Link Prediction
Graph Representation Learning and Beyond (GRL+) Workshop at ICML 2020, 2020. (* Equal contribution) - ICLR 2020Curvature Graph Network
The Eighth International Conference on Learning Representations (ICLR), 2020. - AAAI 2020EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs
The Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI), 2020. (* Equal contribution) - AAAI 2020 OralOnline Planner Selection with Graph Neural Networks and Adaptive Scheduling
The Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI), 2020. - AAAI 2020 TutorialGraph Neural Networks: Models and Applications
Tutorial at the Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI), 2020. - KDD 2020 TutorialDeep Graph Learning: Foundations, Advances and Applications
Tutorial at the ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2020. - EMNLP 2019 WorkshopGraph Enhanced Cross-Domain Text-to-SQL Generation
EMNLP 2019 Workshop on Graph-Based Methods for NLP (TextGraphs), 2019. - TVCG/InfoVis 2019DeepDrawing: A Deep Learning Approach to Graph Drawing
IEEE Transactions on Visualization and Computer Graphics (Proceedings of InfoVis), 2019. - ICML 2019 WorkshopIPC: A Benchmark Data Set for Learning with Graph-Structured Data
ICML 2019 Workshop on Learning and Reasoning with Graph-Structured Data, 2019. - IJCAI 2019Pre-training of Graph Augmented Transformers for Medication Recommendation
The 28th International Joint Conference on Artificial Intelligence (IJCAI), 2019. - AAAI 2019GAMENet: Graph Augmented MEmory Networks for Recommending Medication Combination
The Thirty-Third AAAI Conference on Artificial Intelligence (AAAI), 2019. - arXiv 2019GENN: Predicting Correlated Drug-drug Interactions with Graph Energy Neural Networks
arXiv preprint arXiv:1910.02107, 2019. - NeurIPS 2018 WorkshopScalable Graph Learning for Anti-Money Laundering: A First Look
NeurIPS 2018 Workshop on Challenges and Opportunities for AI in Financial Services: the Impact of Fairness, Explainability, Accuracy, and Privacy (FEAP-AI4Fin), 2018. - NeurIPS 2018Constrained Generation of Semantically Valid Graphs via Regularizing Variational Autoencoders
Neural Information Processing Systems (NeurIPS), 2018. (* Equal contribution) - IJCAI-ECAI 2018Drug Similarity Integration Through Attentive Multi-view Graph Auto-Encoders
The 27th International Joint Conference on Artificial Intelligence and the 23rd European Conference on Artificial Intelligence (IJCAI-ECAI), 2018. - ICLR 2018FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling
The Sixth International Conference on Learning Representations (ICLR), 2018. (* Equal contribution)
Time Series Learning
Interpretable models, shape-based representations, foundation models, and causality-aware anomaly detection.
- SDM 2026SC-JEPA: Stabilizing Latent Predictive Learning for Time-Series Anomaly Prediction
SIAM International Conference on Data Mining (SDM), 2026. (Previously named MTS-JEPA; a preliminary version is also accepted at the ICML 2026 AI Forecasting workshop.) - ECML PKDD 2026Tensor-TimesFM: High-Dimensional Sparse Time Series Forecasting with Tensor Decoders and Latent Dynamics Prediction
Joint European Conference on Machine Learning and Knowledge Discovery in Databases, 2026. - KDD 2026CAAD: Causality-Aware Multivariate Time Series Anomaly Detection via Multi-Scale Alignment and Structural Causal Consistency
The 32nd SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2026. - ICLR 2025Shedding Light on Time Series Classification using Interpretability Gated Networks
The Thirteenth International Conference on Learning Representations (ICLR), 2025. († Corresponding) - NeurIPS 2024Abstracted Shapes as Tokens - A Generalizable and Interpretable Model for Time-series
The Thirty-eighth Annual Conference on Neural Information Processing Systems (NeurIPS), 2024. († Corresponding) - ICLR 2023Weighted Clock Logic Point Process
The Eleventh International Conference on Learning Representations (ICLR), 2023. - ICDM 2022Neuro-symbolic Models for Interpretable Time Series Classification using Temporal Logic Description
The 22nd IEEE International Conference on Data Mining (ICDM), 2022. - IJCAI 2019MINA: Multilevel Knowledge-Guided Attention for Modeling Electrocardiography Signals
The 28th International Joint Conference on Artificial Intelligence (IJCAI), 2019.
Language & Intelligence
Language model transparency and trustworthiness, summarization, representation learning, and AI for code.
- EMNLP 2026 FindingsGuided Permutation Scoring (GPS): Option-Order Permutation for Multiple-Choice Question Answering
The 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP) Findings, 2026. - KDD 2026Domain-Specific Data Synthesis for LLMs through Minimal Sufficient Representation Learning
The 32nd SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2026. - ICML 2026Resting Neurons, Active Insights: Robustify Activation Sparsity for Large Language Models
The 43rd International Conference on Machine Learning (ICML), 2026. - ACL 2026 FindingsHypEHR: Hyperbolic Modeling of Electronic Health Records for Efficient Question Answering
The 64th Annual Meeting of the Association for Computational Linguistics (ACL) Findings, 2026. - ICLR 2026A Problem-Oriented Perspective and Anchor Verification for Code Optimization
The Fourteenth International Conference on Learning Representations (ICLR), 2026. - LoG 2025When Structure Doesn't Help: LLMs Do Not Read Text-Attributed Graphs as Effectively as We Expected
Learning on Graphs Conference (LoG), 2025. - ML4H 2025Concept-Enhanced Automatic ICD Coding using Large Language Models
The AHLI Machine Learning for Health (ML4H) Symposium Proceedings, 2025. - UIST 2025MACEDON: Supporting Programmers with Real-Time Multi-Dimensional Code Evaluation and Optimization
Proceedings of the 38th Annual ACM Symposium on User Interface Software and Technology (UIST), 2025. - ACL 2025 FindingsNBDESCRIB: A Dataset for Text Description Generation from Tables and Code in Jupyter Notebooks with Guidelines
The 63rd Annual Meeting of the Association for Computational Linguistics (ACL) Findings, 2025. - AAAI 2025Uncovering LLM-Generated Code: A Zero-Shot Synthetic Code Detector via Code Rewriting
The Thirty-Ninth AAAI Conference on Artificial Intelligence (AAAI), 2025. (* Equal contribution) - EMNLP 2024FAC2E: Better Understanding Large Language Model Capabilities by Dissociating Language and Cognition
The 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2024. - NAACL 2024 FindingsTram: A Token-level Retrieval-augmented Mechanism for Source Code Summarization
Findings of the North American Chapter of the Association for Computational Linguistics (NAACL Findings), 2024. - AAAI 2024AdaCCD: Adaptive Semantic Contrasts Discovery based Cross Lingual Adaptation for Code Clone Detection
The Thirty-Eighth AAAI Conference on Artificial Intelligence (AAAI), 2024. - EMNLP 2023Knowledge Graph Compression Enhances Diverse Commonsense Generation
The 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2023. - EMNLP 2023CP-BCS: Binary Code Summarization Guided by Control Flow Graph and Pseudo Code
The 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2023. - CHI 2023Slide4N: Creating Presentation Slides from Computational Notebooks with Human-AI Collaboration
The ACM CHI Conference on Human Factors in Computing Systems (CHI), 2023. - NAACL 2022A Study of the Attention Abnormality in Trojaned BERTs
The 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT), 2022. - INFOCOM 2022MalGraph: Hierarchical Graph Neural Networks for Robust Windows Malware Detection
IEEE International Conference on Computer Communications (INFOCOM), 2022. - arXiv 2022Improving long tailed document-level relation extraction via easy relation augmentation and contrastive learning
arXiv preprint arXiv:2205.10511, 2022. - EMNLP 2021Timeline Summarization based on Event Graph Compression via Time-Aware Optimal Transport
The 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2021. - EMNLP 2021 FindingsConstructing contrastive samples via summarization for text classification with limited annotations
Findings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP Findings), 2021. - TKDD 2021Deep Graph Matching and Searching for Semantic Code Retrieval
ACM Transactions on Knowledge Discovery from Data (TKDD), 2021. - IEEE BigData 2020Supervised Topic Compositional Neural Language Model for Clinical Narrative Understanding
IEEE International Conference on Big Data (BigData), 2020. - EMNLP 2020Unsupervised Reference-Free Summary Quality Evaluation via Contrastive Learning
The 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2020. (* Equal contribution) - NeurIPS 2019 WorkshopLearning Logical Representations from Natural Languages with Weak Supervision and Back Translation
NeurIPS 2019 Workshop on Knowledge Representation & Reasoning Meets Machine Learning (KR2ML), 2019. - EMNLP 2019Pre-Training BERT on Domain Resources for Short Answer Grading
Conference on Empirical Methods in Natural Language Processing and International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), 2019. - EMNLP 2019 WorkshopGraph Enhanced Cross-Domain Text-to-SQL Generation
EMNLP 2019 Workshop on Graph-Based Methods for NLP (TextGraphs), 2019. - AIED 2018Preliminary Evaluations of a Dialogue-based Tutor
The 19th International Conference on Artificial Intelligence in Education (AIED), 2018. - ICLS 2018Dialogue-based tutoring at scale: Design and Challenges
The 13th International Conference of the Learning Sciences (ICLS), 2018. - WWW 2018Human-level multiple choice question guessing without domain knowledge: Machine-learning of framing effects
The Web Conference (WWW), Cognitive Computing Track, 2018. - Book Chapter 2018Wizard's Apprentice Powers Testing of Advanced Conversational Intelligent Tutors
Tutoring and Intelligent Tutoring Systems, Chapter 12, Nova Science Pub Inc, 2018. - arXiv 2018AWE: Asymmetric Word Embedding for Textual Entailment
arXiv preprint arXiv:1809.04047, 2018. - IJCAI 2017Inverted Bilingual Topic Models for Lexicon Extraction from Non-parallel Data
Proceedings of the 26th International Joint Conference on Artificial Intelligence (IJCAI), Melbourne, Australia, 2017. - AIED 2017Wizard's Apprentice: Cognitive Suggestion Support for Wizard-of-Oz Question Answering
The 18th International Conference on Artificial Intelligence in Education (AIED), Wuhan, China, 2017. - EACL 2017Multilingual Training of Crosslingual Word Embeddings
Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics (EACL), Valencia, Spain, 2017. - EMNLP 2016Learning Crosslingual Word Embeddings without Bilingual Corpora
Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing (EMNLP), Austin, Texas, USA, pp. 1285–1295, 2016. - AAAI 2015The Hybrid Nested/Hierarchical Dirichlet Process and its Application to Topic Modeling with Word Differentiation
The Twenty-Ninth AAAI Conference on Artificial Intelligence (AAAI-15), Austin, USA, pp. 2835–2841, 2015. - EMNLP 2013Automatically Determining a Proper Length for Multi-document Summarization: A Bayesian Nonparametric Approach
The 2013 Conference on Empirical Methods in Natural Language Processing (EMNLP), Seattle, USA, pp. 736–749, 2013. - IJCNLP 2011Named Entity Recognition in Chinese News Comments on the Web
The 5th International Joint Conference on Natural Language Processing (IJCNLP), pp. 856–864, 2011. - ICDM 2010Multi-Document Summarization Using Minimum Distortion
Proceedings of the 10th IEEE International Conference on Data Mining (ICDM), Sydney, pp. 354–363, 2010. - TAC 2010PKUTM participation at TAC 2010 RTE and summarization track
Proceedings of Text Analysis Conference (TAC), 2010. - COLING 2010Opinion Target Extraction in Chinese News Comments
Proceedings of the 23rd International Conference on Computational Linguistics (COLING), Beijing, pp. 782–790, 2010. - NTCIR-8 2010 OralPKUTM Experiments in NTCIR8 MOAT Task
NTCIR-8, Tokyo, pp. 228–233, 2010. (Oral; * Equal contribution)
AI for Healthcare
Electronic health records, medication recommendation, drug discovery, and computational wound healing.
- MICCAI 2026Spatiotemporal Modeling of Tumor Dynamics via Optimal Transport for Enhanced Longitudinal Analysis
The 29th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), 2026. - ACM BCB 2026Efficient Imputation for Patch-based Tabular Missing Data via Cluster-regularized Optimal Transport
The 17th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics (ACM BCB), 2026. - ACL 2026 FindingsHypEHR: Hyperbolic Modeling of Electronic Health Records for Efficient Question Answering
The 64th Annual Meeting of the Association for Computational Linguistics (ACL) Findings, 2026. - AMIA 2026A Novel Approach to Zero-Shot Drug-Drug Interaction Prediction Enabled by EHR-Augmented Knowledge Graphs
AMIA 2026 Amplify Informatics Conference, 2026. (Poster) - ML4H 2025Concept-Enhanced Automatic ICD Coding using Large Language Models
The AHLI Machine Learning for Health (ML4H) Symposium Proceedings, 2025. - ML4H 2025 FindingsDual-Pathway Fusion of EHRs and Knowledge Graphs for Predicting Unseen Drug-Drug Interactions
The AHLI Machine Learning for Health (ML4H) Symposium Findings Track, 2025. - Sci. Rep. 2025Integrated machine learning analysis of proteomic and transcriptomic data identifies healing associated targets in diabetic wound repair
Scientific Reports, 2025. (* Equal contribution; † Corresponding) - BSPC 2025Quantitative ultrasound augmented with machine learning to assess tissue microstructure during wound healing
Biomedical Signal Processing and Control, Volume 103, 2025. - Adv. Healthc. Mater. 2023A Miniaturized, Battery-free, Wireless Wound Monitor that Predicts Wound Closure Rate Early
Advanced Healthcare Materials, 2023. (* Equal contribution) - TKDE 2022CHEER: Rich Model Helps Poor Model via Knowledge Infusion
IEEE Transactions on Knowledge and Data Engineering (TKDE), 2022. - IEEE BigData 2020Supervised Topic Compositional Neural Language Model for Clinical Narrative Understanding
IEEE International Conference on Big Data (BigData), 2020. - ACM BCB 2019PEARL: Prototype Learning via Rule Learning
ACM Conference on Bioinformatics, Computational Biology, and Health Informatics (ACM BCB), 2019. (* Equal contribution) - IJCAI 2019Pre-training of Graph Augmented Transformers for Medication Recommendation
The 28th International Joint Conference on Artificial Intelligence (IJCAI), 2019. - IJCAI 2019RDPD: Rich Data Helps Poor Data via Imitation
The 28th International Joint Conference on Artificial Intelligence (IJCAI), 2019. - IJCAI 2019MINA: Multilevel Knowledge-Guided Attention for Modeling Electrocardiography Signals
The 28th International Joint Conference on Artificial Intelligence (IJCAI), 2019. - AAAI 2019GAMENet: Graph Augmented MEmory Networks for Recommending Medication Combination
The Thirty-Third AAAI Conference on Artificial Intelligence (AAAI), 2019. - arXiv 2019GENN: Predicting Correlated Drug-drug Interactions with Graph Energy Neural Networks
arXiv preprint arXiv:1910.02107, 2019. - IJCAI-ECAI 2018Drug Similarity Integration Through Attentive Multi-view Graph Auto-Encoders
The 27th International Joint Conference on Artificial Intelligence and the 23rd European Conference on Artificial Intelligence (IJCAI-ECAI), 2018. - PLOS ONE 2018Readmission Prediction via Deep Contextual Embedding of Clinical Concepts
PLOS ONE, 2018. (* Equal contribution) - SDM 2018Health-ATM: A Deep Architecture for Multifaceted Patient Health Record Representation and Risk Prediction
SIAM International Conference on Data Mining (SDM), 2018. (* Equal contribution) - SCIA 2013Automated Tracing of Retinal Blood Vessels Using Graphical Models
Scandinavian Conference on Image Analysis (SCIA), pp. 277–289, 2013.
Others
Other topics, including AI-assisted creative tools, AI for science, and secure model training.
- CHI 2025Influencer: Empowering Everyday Users in Creating Promotional Posts via AI-infused Exploration and Customization
The ACM CHI Conference on Human Factors in Computing Systems (CHI), 2025. - ECCV 2024TrojVLM: Backdoor Attack Against Vision Language Models
European Conference on Computer Vision (ECCV), 2024. - EML 2020Artificial intelligence method to design and fold alpha-helix structural proteins from the primary amino acid sequence
Extreme Mechanics Letters, 2020. (* Equal contribution) - DSN 2019Reaching Data Confidentiality and Model Accountability on the CalTrain
The 49th IEEE/IFIP International Conference on Dependable Systems and Networks (DSN), 2019.