FedMap: Iterative Magnitude-Based Pruning for Communication-Efficient Federated Learningby Alexander Herzog, Robbie Southam, Ioannis Mavromatis, Aftab…
Learn it or Leave it: Module Composition and Pruning for Continual Learningby Mingyang Wang, Heike…
QBI: Quantile-Based Bias Initialization for Efficient Private Data Reconstruction in Federated Learningby Micha V. Nowak,…
Views Can Be Deceiving: Improved SSL Through Feature Space Augmentationby Kimia Hamidieh, Haoran Zhang, Swami…
Learning on Transformers is Provable Low-Rank and Sparse: A One-layer Analysisby Hongkang Li, Meng Wang,…
Geometric Median (GM) Matching for Robust Data Pruningby Anish Acharya, Inderjit S Dhillon, Sujay SanghaviFirst…
ShadowLLM: Predictor-based Contextual Sparsity for Large Language Modelsby Yash Akhauri, Ahmed F AbouElhamayed, Jordan Dotzel,…
Towards Lightweight Graph Neural Network Search with Curriculum Graph Sparsificationby Beini Xie, Heng Chang, Ziwei…
What Matters in Transformers? Not All Attention is Neededby Shwai He, Guoheng Sun, Zheyu Shen,…
Rethinking Pruning Large Language Models: Benefits and Pitfalls of Reconstruction Error Minimizationby Sungbin Shin, Wonpyo…