Publications
- TDSCGraph privacy funnel: A variational approach for privacy-preserving representation learning on graphsIEEE Transactions on Dependable and Secure Computing (TDSC), 2024
- TNNLSDebiasing Graph Representation Learning Based on Information BottleneckIEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2024
- MLSysBe Careful with PyPI Packages: You May Unconsciously Spread Backdoor Model WeightsIn Proceedings of Machine Learning and Systems (MLSys), 2023
- CVPROrphicx: A causality-inspired latent variable model for interpreting graph neural networksIn Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022
- IPDPSEAGLE: Expedited Device Placement with Automatic Grouping for Large ModelsIn 2021 IEEE International Parallel and Distributed Processing Symposium (IPDPS), 2021
- ICMLGenerative causal explanations for graph neural networksIn International Conference on Machine Learning (ICML), 2021
- ICPPAccelerated Device Placement Optimization with Contrastive LearningIn 50th International Conference on Parallel Processing (ICPP), 2021
- Rss: a relay-based schedule scheme for optical data center networkPhotonic Network Communications, 2020
- TCOMThor: a scalable hybrid switching architecture for data centersIEEE Transactions on Communications, 2018
- ICOCNA novel multi-controller flow schedule scheme for fat-tree architectureIn 2016 15th International Conference on Optical Communications and Networks (ICOCN), 2016
- ICOCNOROF: A hybrid topology with high scalability for data center networksIn 2015 14th International Conference on Optical Communications and Networks (ICOCN), 2015