48 citations · 69 across the 13 of their papers we have counts for
8 papers · 1 filter
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…
Stitch the Fragments: One-Shot Hierarchical Federated Clustering
Shenghong Cai, Zihua Yang, Yang Lu +4
Federated Clustering (FC) faces a critical bottleneck in real-world scenarios, i.e., global clusters are rarely intact, often fragmenting into incomplete, multi-granular unlabeled…
Break the Tie: Learning Cluster-Customized Category Relationships for Categorical Data Clustering
Mingjie Zhao, Zhanpei Huang, Yang Lu +4
Categorical attributes with qualitative values are ubiquitous in cluster analysis of real datasets. Unlike the Euclidean distance of numerical attributes, the categorical attribute…
Classifying Long-tailed and Label-noise Data via Disentangling and Unlearning
Chen Shu, Mengke Li, Yiqun Zhang +4
In real-world datasets, the challenges of long-tailed distributions and noisy labels often coexist, posing obstacles to the model training and performance. Existing studies on long…
Asynchronous Federated Clustering with Unknown Number of Clusters
Yunfan Zhang, Yiqun Zhang, Yang Lu +3
Federated Clustering (FC) is crucial to mining knowledge from unlabeled non-Independent Identically Distributed (non-IID) data provided by multiple clients while preserving their p…
HyReaL: Clustering Attributed Graph via Hyper-Complex Space Representation Learning
Junyang Chen, Yang Lu, Mengke Li +3
Clustering complex data in the form of attributed graphs has attracted increasing attention, where powerful graph representation is a critical prerequisite. However, the well-known…
Improve Knowledge Distillation via Label Revision and Data Selection
Weichao Lan, Yiu-ming Cheung, Qing Xu +4
Knowledge distillation (KD) has become a widely used technique in the field of model compression, which aims to transfer knowledge from a large teacher model to a lightweight stude…
Federated Learning with Extremely Noisy Clients via Negative Distillation
Yang Lu, Lin Chen, Yonggang Zhang +4
Federated learning (FL) has shown remarkable success in cooperatively training deep models, while typically struggling with noisy labels. Advanced works propose to tackle label noi…