相关论文: Improving performance in multi-objective decision-…

There are situations where data relevant to machine learning problems are distributed across multiple locations that cannot share the data due to regulatory, competitiveness, or privacy reasons. Machine learning approaches that require data…

At present, robots typically require extensive training to successfully accomplish a single task. However, to truly enhance their usefulness in real-world scenarios, robots should possess the capability to perform multiple tasks…

Recent advances in reinforcement learning (RL) for large language model (LLM) fine-tuning show promise in addressing multi-objective tasks but still face significant challenges, including competing objective balancing, low training…

In reinforcement learning (RL), different reward functions can define the same optimal policy but result in drastically different learning performance. For some, the agent gets stuck with a suboptimal behavior, and for others, it solves the…

Deploying large Transformer-based vision models on resource-limited mobile devices at network edge is severely constrained by hardware limitations and dynamic wireless environments. While federated learning (FL) enables collaborative…

Reinforcement learning (RL) using foundation models for policy approximations in multi-turn tasks remains challenging. We identify two main limitations related to sparse reward settings and policy gradient updates, based on which we…

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…

Modern multi-agent reinforcement learning frameworks rely on centralized training and reward shaping to perform well. However, centralized training and dense rewards are not readily available in the real world. Current multi-agent…

Quadrupedal locomotion is a complex, open-ended problem vital to expanding autonomous vehicle reach. Traditional reinforcement learning approaches often fall short due to training instability and sample inefficiency. We propose a novel…

An emerging field of sequential decision problems is safe Reinforcement Learning (RL), where the objective is to maximize the reward while obeying safety constraints. Being able to handle constraints is essential for deploying RL agents in…

Multi-task learning uses auxiliary data or knowledge from relevant tasks to facilitate the learning in a new task. Multi-task optimization applies multi-task learning to optimization to study how to effectively and efficiently tackle…

Federated Learning (FL) has evolved as a promising technique to handle distributed machine learning across edge devices. A single neural network (NN) that optimises a global objective is generally learned in most work in FL, which could be…

Multi-Objective Alignment aims to align Large Language Models (LLMs) with diverse and often conflicting human values by optimizing multiple objectives simultaneously. Existing methods predominantly rely on static preference weight…

We introduce a new algorithm for multi-objective reinforcement learning (MORL) with linear preferences, with the goal of enabling few-shot adaptation to new tasks. In MORL, the aim is to learn policies over multiple competing objectives…

Softmax Loss (SL) is being increasingly adopted for recommender systems (RS) as it has demonstrated better performance, robustness and fairness. Yet in implicit-feedback, a single global temperature and equal treatment of uniformly sampled…

Large language models (LLMs), despite possessing latent safety understanding from their vast pretraining data, remain vulnerable to generating harmful content and exhibit issues such as over-refusal and utility degradation after safety…

Meta-Learning (ML) has proven to be a useful tool for training Few-Shot Learning (FSL) algorithms by exposure to batches of tasks sampled from a meta-dataset. However, the standard training procedure overlooks the dynamic nature of the…

Bias originates from both data and algorithmic design, often exacerbated by traditional fairness methods that fail to address the subtle impacts of protected attributes. This study introduces an approach to mitigate bias in machine learning…

Large language models (LLMs) have been widely adopted due to their remarkable performance across various applications, driving the accelerated development of a large number of diverse models. However, these individual LLMs show limitations…

Fine-tuning pre-trained large language models (LLMs) in a distributed manner poses significant challenges on resource-constrained edge networks. To address this challenge, we propose SflLLM, a novel framework that integrates split federated…