8 citations · 23 across the 12 of their papers we have counts for
7 papers · 1 filter
Beyond Peak Backlog: Conditional Energy and Temporal Geometry in Capacity-Constrained Delayed Bandit Optimization
Anling Xiang, Yuwen Yang, Yang Shen
What is the right delay complexity when a learner can track only pending feedback items and discarded feedback is permanently lost? Existing one-point bandit convex optimizatio…
Federated Multi-Task Learning on Non-IID Data Silos: An Experimental Study
Yuwen Yang, Yuxiang Lu, Suizhi Huang +3
The innovative Federated Multi-Task Learning (FMTL) approach consolidates the benefits of Federated Learning (FL) and Multi-Task Learning (MTL), enabling collaborative model traini…
UNIDEAL: Curriculum Knowledge Distillation Federated Learning
Yuwen Yang, Chang Liu, Xun Cai +3
Federated Learning (FL) has emerged as a promising approach to enable collaborative learning among multiple clients while preserving data privacy. However, cross-domain FL tasks, w…
Position-Aware Subgraph Neural Networks with Data-Efficient Learning
Chang Liu, Yuwen Yang, Zhe Xie +2
Data-efficient learning on graphs (GEL) is essential in real-world applications. Existing GEL methods focus on learning useful representations for nodes, edges, or entire graphs wi…
EDEN: A Plug-in Equivariant Distance Encoding to Beyond the 1-WL Test
Chang Liu, Yuwen Yang, Yue Ding +1
The message-passing scheme is the core of graph representation learning. While most existing message-passing graph neural networks (MPNNs) are permutation-invariant in graph-level…
Completely Heterogeneous Federated Learning
Chang Liu, Yuwen Yang, Xun Cai +2
Federated learning (FL) faces three major difficulties: cross-domain, heterogeneous models, and non-i.i.d. labels scenarios. Existing FL methods fail to handle the above three cons…
NoMorelization: Building Normalizer-Free Models from a Sample's Perspective
Chang Liu, Yuwen Yang, Yue Ding +1
The normalizing layer has become one of the basic configurations of deep learning models, but it still suffers from computational inefficiency, interpretability difficulties, and l…