25 citations · 87 across the 56 of their papers we have counts for
5 papers · 1 filter
FedTune: A Deep Dive into Efficient Federated Fine-Tuning with Pre-trained Transformers
Jinyu Chen, Wenchao Xu, Song Guo +3
Federated Learning (FL) is an emerging paradigm that enables distributed users to collaboratively and iteratively train machine learning models without sharing their private data.…
PMR: Prototypical Modal Rebalance for Multimodal Learning
Yunfeng Fan, Wenchao Xu, Haozhao Wang +2
Multimodal learning (MML) aims to jointly exploit the common priors of different modalities to compensate for their inherent limitations. However, existing MML methods often optimi…
ProCC: Progressive Cross-primitive Compatibility for Open-World Compositional Zero-Shot Learning
Fushuo Huo, Wenchao Xu, Song Guo +4
Open-World Compositional Zero-shot Learning (OW-CZSL) aims to recognize novel compositions of state and object primitives in images with no priors on the compositional space, which…
FR: Folded Rationalization with a Unified Encoder
Wei Liu, Haozhao Wang, Jun Wang +3
Conventional works generally employ a two-phase model in which a generator selects the most important pieces, followed by a predictor that makes predictions based on the selected p…
Sign Bit is Enough: A Learning Synchronization Framework for Multi-hop All-reduce with Ultimate Compression
Feijie Wu, Shiqi He, Song Guo +4
Traditional one-bit compressed stochastic gradient descent can not be directly employed in multi-hop all-reduce, a widely adopted distributed training paradigm in network-intensive…