3 citations · 10 across the 12 of their papers we have counts for
7 papers · 1 filter
Privacy-Preserving Communication-Efficient Federated Multi-Armed Bandits
Tan Li, Linqi Song
Communication bottleneck and data privacy are two critical concerns in federated multi-armed bandit (MAB) problems, such as situations in decision-making and recommendations of con…
CSAGN: Conversational Structure Aware Graph Network for Conversational Semantic Role Labeling
Han Wu, Kun Xu, Linqi Song
Conversational semantic role labeling (CSRL) is believed to be a crucial step towards dialogue understanding. However, it remains a major challenge for existing CSRL parser to hand…
Byzantine-robust Federated Learning through Collaborative Malicious Gradient Filtering
Jian Xu, Shao-Lun Huang, Linqi Song +1
Gradient-based training in federated learning is known to be vulnerable to faulty/malicious clients, which are often modeled as Byzantine clients. To this end, previous work either…
DQ-SGD: Dynamic Quantization in SGD for Communication-Efficient Distributed Learning
Guangfeng Yan, Shao-Lun Huang, Tian Lan +1
Gradient quantization is an emerging technique in reducing communication costs in distributed learning. Existing gradient quantization algorithms often rely on engineering heuristi…
Domain-Adaptive Pretraining Methods for Dialogue Understanding
Han Wu, Kun Xu, Linfeng Song +3
Language models like BERT and SpanBERT pretrained on open-domain data have obtained impressive gains on various NLP tasks. In this paper, we probe the effectiveness of domain-adapt…
Coded Alternating Least Squares for Straggler Mitigation in Distributed Recommendations
Siyuan Wang, Qifa Yan, Jingjing Zhang +2
Matrix factorization is an important representation learning algorithm, e.g., recommender systems, where a large matrix can be factorized into the product of two low dimensional ma…
Conversational Semantic Role Labeling
Kun Xu, Han Wu, Linfeng Song +3
Semantic role labeling (SRL) aims to extract the arguments for each predicate in an input sentence. Traditional SRL can fail to analyze dialogues because it only works on every sin…