12 papers
Avoiding Structural Failure Modes in Tabular Fair SSL: Online Primal-Dual Allocation under Confidence Gating
Hangchuan Liang, Changchun Li
Semi-supervised learning (SSL) enables prediction with limited labels, but high-stakes tabular applications (medical, credit, recidivism) require statistical fairness guarantees. W…
Are Rationales Necessary and Sufficient? Tuning LLMs for Explainable Misinformation Detection
Bing Wang, Rui Miao, Ximing Li +6
The rapid spread of misinformation on social media platforms has become a formidable challenge. To mitigate its proliferation, Misinformation Detection (MD) has emerged as a critic…
Decomposing the Basic Abilities of Large Language Models: Mitigating Cross-Task Interference in Multi-Task Instruct-Tuning
Bing Wang, Ximing Li, Changchun Li +3
Recently, the prominent performance of large language models (LLMs) has been largely driven by multi-task instruct-tuning. Unfortunately, this training paradigm suffers from a key…
Generalizing Dynamics Modeling More Easily from Representation Perspective
Yiming Wang, Zhengnan Zhang, Genghe Zhang +7
Learning system dynamics from observations is a critical problem in many applications over various real-world complex systems, e.g., climate, ecology, and fluid systems. Recently,…
Learning from Label Proportions with Dual-proportion Constraints
Tianhao Ma, Ximing Li, Changchun Li +1
Learning from Label Proportions (LLP) is a weakly supervised problem in which the training data comprise bags, that is, groups of instances, each annotated only with bag-level clas…
Semi-Supervised Learning with Balanced Deep Representation Distributions
Changchun Li, Ximing Li, Bingjie Zhang +2
Semi-Supervised Text Classification (SSTC) mainly works under the spirit of self-training. They initialize the deep classifier by training over labeled texts; and then alternativel…