Xian‐Sheng Hua

Cross-Domain Empirical Risk Minimization for Unbiased Long-Tailed Classification

2022 · Proceedings of the AAAI Conference on Artificial Intelligence

We address the overlooked unbiasedness in existing long-tailed classification methods: we find that their overall improvement is mostly attributed to the biased preference of "tail" over "head", as the test distribution is assumed to be …

TGNN: A Joint Semi-supervised Framework for Graph-level Classification

2022

This paper studies semi-supervised graph classification, a crucial task with a wide range of applications in social network analysis and bioinformatics. Recent works typically adopt graph neural networks to learn graph-level representations for classification, failing …

Learning with Imbalanced Noisy Data by Preventing Bias in Sample Selection

2024 · arXiv (Cornell University)

Learning with noisy labels has gained increasing attention because the inevitable imperfect labels in real-world scenarios can substantially hurt the deep model performance. Recent studies tend to regard low-loss samples as clean ones and discard …

Anti-Collapse Loss for Deep Metric Learning Based on Coding Rate Metric

2024 · arXiv (Cornell University)

Deep metric learning (DML) aims to learn a discriminative high-dimensional embedding space for downstream tasks like classification, clustering, and retrieval. Prior literature predominantly focuses on pair-based and proxy-based methods to maximize inter-class discrepancy and minimize …

SPORT: A Subgraph Perspective on Graph Classification with Label Noise

2024 · ACM Transactions on Knowledge Discovery from Data

Graph neural networks (GNNs) have achieved great success recently on graph classification tasks using supervised end-to-end training. Unfortunately, extensive noisy graph labels could exist in the real world because of the complicated processes of manual …