Here is a selection of recent papers by the PDML Lab, arranged by topic. Additional publications are available from our faculty web pages (Feng)
Robust AI for Out-of-Distribution Detection and Generalization
- VGX: Large-Scale Sample Generation for Boosting Learning-Based Software Vulnerability Analyses
Yu Nong, Richard Fang, Guangbei Yi, Kunsong Zhao, Xiapu Luo, Feng Chen, and Haipeng Cai.
In IEEE/ACM International Conference on Software Engineering (ICSE), 2024. (To Appear) - Bridging the gap between spatial and spectral domains: A unified framework for graph neural networks
Zhiqian Chen, Fanglan Chen, Lei Zhang, Taoran Ji, Kaiqun Fu, Liang Zhao, Feng Chen, Lingfei Wu, Charu Aggarwal, and Chang-Tien Lu
(ACM Computing Survey), 2023 (Impact factor: 16.6). (To Appear) - Evading Provenance-Based ML Detectors with Adversarial System Actions
Kunal Mukherjee, Joshua Wiedemeier, Tianhao Wang, James Wei, Feng Chen, Muhyun Kim, Murat Kantarcioglu, Kangkook Jee
Proceedings of The 32nd USENIX Security Symposium (USENIX 2023), 2023. (To Appear) - VulGen: Realistic Vulnerable Sample Generation via Pattern Mining and Deep Learning.
Yu Nong, Yuzhe Ou, Michael Pradel, Feng Chen, and Haipeng Cai.
Proceedings of IEEE/ACM International Conference on Software Engineering (ICSE 2023), 2023. (To Appear) - SCM-VAE: Learning Identifiable Causal Representations via Structural Knowledge.
Aneesh Komanduri, Yongkai Wu, Wen Huang, Feng Chen, and Xintao Wu
Proceedings of the IEEE International Conference on Big Data (IEEE BigData), 2022. (Acceptance rate: 17%) - Defending Evasion Attacks via Adversarially Adaptive Training.
Minh-Hao Van, Wei Du, Xintao Wu, Feng Chen, Aidong Lu
Proceedings of the IEEE International Conference on Big Data (IEEE BigData), 2022. (Acceptance rate: 17%) - Generating Realistic Vulnerabilities via Neural Code Editing: An Empirical Study.
Yu Nong, Yuzhe Ou, Michael Pradel, Feng Chen, and Haipeng Cai.
Proceedings of ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE 2022), pages 1097–1109, 2023. (artifact evaluated; badges: Available, Functional). - How Out-of-Distribution Data Hurts Semi-Supervised Learning.
Xujiang Zhao, Krishnateja Killamsetty, Rishabh Iyer, and Feng Chen
Proceedings of the IEEE International Conference on Data Mining (ICDM 2022), 2022. (To Appear; 9% Acceptance Rate for Regular/Full Papers) - Framing Algorithmic Recourse for Anomaly Detection.
Debanjan Datta, Feng Chen, and Naren Ramakrishnan.
Proceedings of the 28th ACM SIGKDD conference on knowledge discovery and data mining (KDD 2022), 2022. (Acceptance rate: 14.99%) - PLATINUM: Semi-Supervised Model Agnostic Meta-Learning using Submodular Mutual Information.
Changbin Li, Suraj Kothawade, Feng Chen, and Rishabh Iyer.
Proceedings of the International Conference of Machine Learning (ICML 2022), 2022. - Calibrated Nonparametric Scan Statistics for Anomalous Pattern Detection in Graphs.
Chunpai Wang, Daniel Neill, Feng Chen
Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI), 2022. (Acceptance Rate: 15%, and Selected for Oral Presentation (< 5%)) [PDF] - Nested Bi-level Optimization Framework for Robust Few Shot Learning.
Krishnateja Killamsetty, Changbin Li, Chen Zhou, Feng Chen, Rishabh Iyer
Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI), 2022 (Acceptance rate: 15%) - Layer Adaptive Deep Neural Networks for Out-of-distribution Detection.
Haoliang Wang, Chen Zhao, Xujiang Zhao, and Feng Chen.
Proceedings of the 26th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD), (PAKDD 2022), 2022. (Acceptance rate: 19.3%) - Robust Semi-Supervised Learning with Out of Distribution Data.
Xujiang Zhao, Killamsetty Krishnateja, Rishabh Iyer, Feng Chen
arXiv:2010.03658, 2021 - A Reweighted Meta Learning Framework for Robust Few Shot Learning.
Krishnateja Killamsetty, Changbin Li, Chen Zhou, Rishabh Iyer, and Feng Chen.
NeurIPS 2021 Workshop on Meta-Learning, (MetaLearn 2021), 2021 (To Appear). - RETRIEVE: Coreset Selection for Efficient and Robust Semi-Supervised Learning.
Krishnateja Killamsetty, Xujiang Zhou, Feng Chen, and Rishabh Iyer.
Proceedings of the Thirty-Five Neural Information Processing Systems, (NeurIPS 2021), 2021 (To Appear). - Distributionally Robust Optimization for Deep Kernel Multiple Instance
Learning.
Hitesh Sapkota, Yiming Ying, Feng Chen, and Qi Yu.
Proceedings of the Twenty-Fourth International Conference on Artificial Intelligence and Statistics (AISTATS), 2021 (To Appear). - Structured Sparsity Model Based Trajectory Tracking Using Private Location Data Release
Minglai Zhao, Jianxin Li, Qiben Yan, Feng Chen, Hongyi Huang, and Xunxun Chen
IEEE Transactions on Dependable and Secure Computing (TDSC), 2020 (To Appear). - A Bisubmodular Approach to Event Detection and Prediction in Multivariate Social Graphs
Shuai Zhang, Haoyi Zhou, Feng Chen, and Jianxin Li
IEEE Transactions on Computational Social Systems (TCSS), 2020 (To Appear). - Online Flu Epidemiological Deep Modeling on Disease Contact Network
Liang Zhao, Jiangzhuo Chen, Feng Chen, Fang Jin, Wei Wang, Chang-Tien Lu, and Naren Ramakrishnan
Journal of GeoInformatica, vol. 24, no. 2, pp. 443-475, 2020. - Efficient Learning with Exponentially-Many Conjunctive Precursors to Forecast Spatial Events
Liang Zhao, Feng Chen, and Yanfang Ye,
IEEE Transactions on Knowledge and Data Engineering (TKDE), vol. 32, iss. 10,pp. 1923-1935, 2019. - PDFM: A Primal-Dual Fairness-Aware Framework for Meta-learning
Chen Zhao, Feng Chen, Zhuoyi Wang, and Latifur Khan
CoRR abs/2009.12675, 2020.
Uncertainty Quantification and Reasoning in AI Safety
- Uncertainty-aware Graph-based Hyperspectral Image Classification.
Linlin Yu, Yifei Lou, and Feng Chen.
Proceeding of the International Conference on Learning Representations (ICLR), 2024 (To Appear) - Hyper Evidential Deep Learning to Quantify Composite Classification Uncertainty.
Changbin Li, Kangshuo Li, Yuzhe Ou, Lance M. Kaplan, Audun Jøsang , Dong H. Jeong, Jin-Hee Cho, Feng Chen.
Proceeding of the International Conference on Learning Representations (ICLR), 2024 (To Appear) - Improvements on Uncertainty Quantification for Node Classification via Distance Based Regularization
Russell Alan Hart, Linlin Yu, Yifei Lou, and Feng Chen
Thirty-Seventh Conference on Neural Information Processing Systems (NeurIPS), 2023. (To Appear) - A Survey on Uncertainty Reasoning and Quantification in Belief Theory and Its Application to Deep Learning
Zhen Guo, Zelin Wan, Qisheng Zhang, Xujiang Zhao, Qi Zhang, Lance M. Kaplan, Dong H. Jeong, Feng Chen, Jin-Hee Cho
(Information Fusion), 2023 (Impact factor: 17.564). (To Appear) - Boosting Cross-Lingual Transfer via Self-Learning with Uncertainty Estimation.
Liyan Xu, Xuchao Zhang, Xujiang Zhao, Haifeng Chen, Feng Chen and Jinho D. Choi.
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP 2021), 2021 (To Appear). - Multidimensional Uncertainty-Aware Evidential Neural Networks.
Yibo Hu, Yuzhe Ou, Xujiang Zhao, Jin-Hee Cho, and Feng Chen.
Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI), 2021 (To Appear). [PDF] - CSL+: Scalable Collective Subjective Logic under Multidimensional Uncertainty
Adil Alim, Jin-Hee Cho, and Feng Chen
ACM Transactions on Intelligent Systems and Technology (TIST), 2020. (To Appear) [PDF] - Uncertainty Aware Semi-Supervised Learning on Graph Data
Xujiang Zhao, Feng Chen, Shu Hu, and Jin-Hee Cho
Thirty-fourth Conference on Neural Information Processing Systems (NeurIPS), 2020. (Spotlight acceptance rate: 4%) [PDF] - Multifaceted Uncertainty Estimation for Label-Efficient Deep Learning
Wei Shi, Xujiang Zhao, Feng Chen, and Qi Yu
Thirty-fourth Conference on Neural Information Processing Systems (NeurIPS), 2020. [PDF] - A Primal-Dual Subgradient Approach for Fair Meta Learning
Chen Zhao, Feng Chen, Zhuoyi Wang, and Latifur Khan
in Proceedings of the IEEE International Conference on Data Mining (ICDM 2020), 2020. (Regular paper; acceptance rate: 9.8%) [PDF] - Detecting Media Self-Censorship without Explicit Training Data
Rong Rong Tao, Baojian Zhou, Feng Chen, David Mares, Patrick Butler, Naren Ramakrishnan, and Ryan Kennedy
in Proceedings of the 2020 SIAM International Conference on Data Mining (SDM), pp. 550-558, 2020. [PDF]
Algorithmic Fairness and Equity in AI
- Dynamic Environment Responsive Online Meta-Learning with Fairness Awareness.
Chen Zhao, Feng Mi, Xintao Wu, Kai Jiang, Latifur Khan, Feng Chen.
The ACM Transactions on Knowledge Discovery from Data (TKDD), 2024. (To Appear) - Towards Fair Disentangled Online Learning for Changing Environments.
Chen Zhao, Feng Mi, Xintao Wu, Kai Jiang, Latifur Khan, Christian Grant, Feng Chen.
Proceedings of the 29th ACM SIGKDD conference on knowledge discovery and data mining (KDD 2023), 2023. (To Appear) - Adaptive Fairness-Aware Online Meta-Learning for Changing Environments.
Chen Zhao, Feng Mi, Xintao Wu, Kai Jiang, Latifur Khan, Feng Chen.
Proceedings of the 28th ACM SIGKDD conference on knowledge discovery and data mining (KDD 2022), 2022. (Acceptance rate: 14.99%) - Fairness-Aware Online Meta-learning.
Chen Zhao, Feng Chen, and Bhavani Thuraisingham.
Proceedings of the 27th ACM SIGKDD conference on knowledge discovery and data mining (KDD 2021), 2021. [PDF] - Fair Meta-Learning For Few-Shot Classification
Chen Zhao, Changbin Li, Jincheng Li, and Feng Chen
in Proceedings of the IEEE International Conference on Knowledge Graph (ICKG), pp. 275-282, 2020. [PDF] - Unfairness Discovery and Prevention For Few-Shot Regression
Chen Zhao and Feng Chen
in Proceedings of the IEEE International Conference on Knowledge Graph (ICKG), pp. 137-144, 2020. [PDF]