Related papers: PRISM: Exposing and Resolving Spurious Isolation i…
As Large Language Models (LLMs) push the boundaries of AI capabilities, their demand for data is growing. Much of this data is private and distributed across edge devices, making Federated Learning (FL) a de-facto alternative for…
As revealed by the scaling law of fine-grained MoE, model performance ceases to be improved once the granularity of the intermediate dimension exceeds the optimal threshold, limiting further gains from single-dimension fine-grained design.…
Federated Learning (FL) has recently emerged as a promising method that employs a distributed learning model structure to overcome data privacy and transmission issues paused by central machine learning models. In FL, datasets collected…
Federated learning (FL) often degrades when clients hold heterogeneous non-Independent and Identically Distributed (non-IID) data and when some clients behave adversarially, leading to client drift, slow convergence, and high communication…
Federated fine-tuning of large language models (LLMs) with low-rank adaptation (LoRA) offers a communication-efficient and privacy-preserving solution for task-specific adaptation. Naive aggregation of LoRA modules introduces noise due to…
This paper explores the challenges of implementing Federated Learning (FL) in practical scenarios featuring isolated nodes with data heterogeneity, which can only be connected to the server through wireless links in an infrastructure-less…
Federated Ranking Learning (FRL) is a state-of-the-art FL framework that stands out for its communication efficiency and resilience to poisoning attacks. It diverges from the traditional FL framework in two ways: 1) it leverages discrete…
Federated learning is a distributed paradigm that aims at training models using samples distributed across multiple users in a network while keeping the samples on users' devices with the aim of efficiency and protecting users privacy. In…
Mixture-of-Experts (MoE) has become a dominant architecture for scaling large language models (LLMs). However, the execution characteristics of MoE inference are changing rapidly and increasingly mismatch the assumptions underlying existing…
Federated learning (FL) is an emerging paradigm that permits a large number of clients with heterogeneous data to coordinate learning of a unified global model without the need to share data amongst each other. A major challenge in…
Finetuning large language models (LLMs) in federated learning (FL) settings has become increasingly important as it allows resource-constrained devices to finetune a model using private data. However, finetuning LLMs using backpropagation…
Data privacy remains a critical concern in educational research, requiring strict adherence to ethical standards and regulatory protocols. While traditional approaches rely on anonymization and centralized data collection, they often expose…
Federated learning (FL) is a distributed learning technique that trains a shared model over distributed data in a privacy-preserving manner. Unfortunately, FL's performance degrades when there is (i) variability in client characteristics in…
Federated efficient fine-tuning has emerged as an approach that leverages distributed data and computational resources across nodes to address the challenges of large-scale fine-tuning and privacy preservation. The Low-Rank Adaptation…
Reinforcement Learning with Verifiable Rewards (RLVR) has become the standard paradigm for LLM mathematical reasoning, with Group Relative Policy Optimization (GRPO) serving as the dominant algorithm. We identify two overlooked…
Imitation learning enables robots to acquire manipulation skills from demonstrations, yet deploying a policy across tasks with heterogeneous dynamics remains challenging, as models tend to average over distinct behavioral modes present in…
The primary challenge in Federated Learning (FL) is to model non-IID distributions across clients, whose fine-grained structure is important to improve knowledge sharing. For example, some knowledge is globally shared across all clients,…
Federated learning (FL) allows remote clients to train a global model collaboratively while protecting client privacy. Despite its privacy-preserving benefits, FL has significant drawbacks, including slow convergence, high communication…
Federated learning (FL) enables collaborative learning of computer vision models, where privacy and regulatory constraints prevent centralizing data across devices or organizations. However, practical FL deployments often exhibit severe…
We consider a federated learning (FL) system consisting of multiple clients and a server, where the clients aim to collaboratively learn a common decision model from their distributed data. Unlike the conventional FL framework that assumes…