18 papers
GRACE: LLM-Grounded Semantic Metric Spaces for Scalable Mixed-Data Clustering
Zihua Yang, Zhencheng Xie, Junyang Chen +4
Clustering mixed tabular data requires a unified metric space to bridge the inherent heterogeneity between continuous numerical measurements and discrete categorical symbols. Tradi…
AnchorMoE: Interpretable Time Series Classification via Anchor-Routed MoE
Tao Xie, Zexi Tan, Haoyi Xiao +5
Multivariate time series classification (MTSC) is pivotal in high-stakes domains, such as clinical diagnosis and industrial fault detection, where safe deployment necessitates tran…
CARE: Class-Adaptive Expert Consensus for Reliable Learning with Long-Tailed Noisy Labels
Mengke Li, Haiquan Ling, Lihao Chen +3
Learning from real-world data is frequently hindered by the compound challenge of long-tailed class distributions and noisy annotations. Existing methods partially address these is…
Decision Boundary-aware Generation for Long-tailed Learning
Jiacheng Yang, Ruichi Zhang, Chikai Shang +5
Long-tailed data bias decision boundaries toward head classes and degrade tail class accuracy. Diffusion-based generative augmentation address this problem by generating additional…
CUE: Concept-Aware Multi-Label Expansion to Mitigate Concept Confusion in Long-Tailed Learning
Ruichi Zhang, Chikai Shang, Jiacheng Yang +4
Long-tailed distributions are common in real-world recognition tasks, where a few head classes have many samples while most tail classes have very few. Recently, fine-tuning founda…
SECOS: Semantic Capture for Rigorous Classification in Open-World Semi-Supervised Learning
Hezhao Liu, Jiacheng Yang, Junlong Gao +4
In open-world semi-supervised learning (OWSSL), a model learns from labeled data and unlabeled data containing both known and novel classes. In practical OWSSL applications, models…