Explainability-guided partial privileged learning: a class-aware weighted similarity approach

Knowing Beyond the Known: Reinforced Knowledge Specification for Multi-Label Class-Incremental Learning

Existing class-incremental learning methods struggle in multi-label scenarios (MLCIL) due to the inherent contradiction of learning objectives arising from co-occurring and incomplete labels. We argue that the core obstacle is the model's ambiguous boundary between known and unknown knowledge, which undermines historic...

Learning Local Feature Masks with Variational Information Bottleneck

Instance-wise feature selection (IWFS) identifies informative features for each instance, improving generalization by discarding irrelevant information and enhancing interpretability through personalized explanations. Most IWFS methods adopt a selector--predictor architecture, where a selector generates instance-specif...

Quantifying the Value of Privileged Information Using a PAC-Bayesian Approach

An algorithm-agnostic, information-theoretic approach based on the PAC-Bayes framework is introduced that quantifies the potential of privileged features before committing to a model, and takes a necessary step toward an information-theoretic understanding of LUPI.

DMatch: distinguish confusing classes with unlabeled data for semi-supervised learning (ChinaMM 2026)

HCCL: Hierarchical Consistency-Driven Contrastive Learning for Semi-Supervised Learning

This work introduces an optimal transport-based online clustering mechanism to automatically discover latent coarse-grained and fine-grained semantic priors without external supervision and introduces a cross-granularity alignment module that enforces consistency between these discovered latent structures and the targe...

Structural knowledge-guided complex-noise handling for open intent classification.

Open intent classification aims to assign known intents to their corresponding classes while identifying unknown intents. Its success largely relies on accurately annotated data. However, real-world data often contains both in-distribution (IND) noise and out-of-distribution (OOD) noise, which degrades model performanc...