5 papers
Resource-Efficient Pruning for Transformer via Low-Rank Importance Estimation
Peng Liu, Huibing Zeng, Yiqun Zhang +2
With the rapid development of large-scale pre-trained language models based on Transformer architectures, their high computational and memory costs have become a major obstacle to…
Imputation Meets Clustering: Exploiting Latent Subgroup Structure for Missing Data Recovery
Chuyao Zhang, E Li, Taochen Chen +5
Missing data is prevalent in practical applications, making effective imputation an essential preprocessing step for downstream analysis. Real-world datasets often exhibit complex…
One-Shot Federated Clustering of Non-Independent Completely Distributed Data
Yiqun Zhang, Shenghong Cai, Zihua Yang +3
Federated Learning (FL) that extracts data knowledge while protecting the privacy of multiple clients has achieved remarkable results in distributed privacy-preserving IoT systems,…
TFEC: Multivariate Time-Series Clustering via Temporal-Frequency Enhanced Contrastive Learning
Zexi Tan, Tao Xie, Haoyi Xiao +5
Multivariate Time-Series (MTS) clustering is crucial for signal processing and data analysis. Although deep learning approaches, particularly those leveraging Contrastive Learning…
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…