Publications

Graph privacy funnel: A variational approach for privacy-preserving representation learning on graphs

Debiasing Graph Representation Learning Based on Information Bottleneck

Be Careful with PyPI Packages: You May Unconsciously Spread Backdoor Model Weights

Orphicx: A causality-inspired latent variable model for interpreting graph neural networks

EAGLE: Expedited Device Placement with Automatic Grouping for Large Models

Generative causal explanations for graph neural networks

Accelerated Device Placement Optimization with Contrastive Learning

Rss: a relay-based schedule scheme for optical data center network

Thor: a scalable hybrid switching architecture for data centers

A novel multi-controller flow schedule scheme for fat-tree architecture

OROF: A hybrid topology with high scalability for data center networks