Research author
Wei Pang
2 AI research papers in the One9Founders library, with summaries and links to original sources.
Papers by Wei Pang
MIDST Challenge at SaTML 2025: Membership Inference over Diffusion-models-based Synthetic Tabular data
Masoumeh Shafieinejad, Xi He, Mahshid Alinoori, et al.
This paper describes the MIDST challenge, which evaluates how well synthetic tabular data generated by diffusion models protects privacy against membership inference attacks (MIAs)—attacks that try to determine if someone's data was used in training. The challenge developed new attack methods and tested diffusion models on both simple and complex relational data to assess whether synthetic data truly provides privacy protection as commonly assumed.
Position: Spectral GNNs Are Neither Spectral Nor Superior for Node Classification
Qin Jiang, Chengjia Wang, Michael Lones, et al.
This paper challenges the theoretical foundations of Spectral Graph Neural Networks (GNNs), arguing they don't actually work as advertised for classifying nodes in graphs. The authors reveal that the mathematical 'frequency-domain filtering' these models claim to perform isn't theoretically sound, and their actual success comes from message-passing mechanics rather than spectral properties. They demonstrate that when spectral models are implemented correctly according to their design, they perform poorly—suggesting their reported effectiveness is due to implementation quirks that accidentally make them behave like simpler, non-spectral neural networks.