Related papers: Pareto Low-Rank Adapters: Efficient Multi-Task Lea…

Preference alignment is a critical step in making Large Language Models (LLMs) useful and aligned with (human) preferences. Existing approaches such as Reinforcement Learning from Human Feedback or Direct Preference Optimization typically…

Effectively leveraging private datasets remains a significant challenge in developing foundation models. Federated Learning (FL) has recently emerged as a collaborative framework that enables multiple users to fine-tune these models while…

We study online preference-based reinforcement learning (PbRL) with the goal of improving sample efficiency. While a growing body of theoretical work has emerged-motivated by PbRL's recent empirical success, particularly in aligning large…

Fine-tuning large language models (LLMs) is crucial for improving their performance on downstream tasks, but full-parameter fine-tuning (Full-FT) is computationally expensive and memory-intensive. Parameter-efficient fine-tuning (PEFT)…

Prior parameter-efficient fine-tuning (PEFT) algorithms reduce memory usage and computational costs of fine-tuning large neural network models by training only a few additional adapter parameters, rather than the entire model. However, the…

Parameter-efficient fine-tuning (PEFT) has become the standard approach for adapting large language models under limited compute and memory budgets. Although previous methods improve efficiency through low-rank updates, quantization, or…

Class-Incremental Learning (CIL) aims to learn new classes sequentially while retaining the knowledge of previously learned classes. Recently, pre-trained models (PTMs) combined with parameter-efficient fine-tuning (PEFT) have shown…

Human Activity Recognition is a foundational task in pervasive computing. While recent advances in self-supervised learning and transformer-based architectures have significantly improved HAR performance, adapting large pretrained models to…

Federated Learning (FL) aims to learn a single global model that enables the central server to help the model training in local clients without accessing their local data. The key challenge of FL is the heterogeneity of local data in…

Catastrophic forgetting has remained a critical challenge for deep neural networks in Continual Learning (CL) as it undermines consolidated knowledge when learning new tasks. Parameter efficient fine tuning CL techniques are gaining…

Preference learning is a widely adopted post-training technique that aligns large language models (LLMs) to human preferences and improves specific downstream task capabilities. In this work we systematically investigate how specific…

Personalized Federated Learning (pFL) holds immense promise for tailoring machine learning models to individual users while preserving data privacy. However, achieving optimal performance in pFL often requires a careful balancing act…

Reward functions are difficult to design and often hard to align with human intent. Preference-based Reinforcement Learning (RL) algorithms address these problems by learning reward functions from human feedback. However, the majority of…

Fine-tuning large vision models (LVMs) and large language models (LLMs) under differentially private federated learning (DPFL) is hindered by a fundamental privacy-utility trade-off. Low-Rank Adaptation (LoRA), a promising…

Many machine learning tasks aim to find models that work well not for a single, but for a group of criteria, often opposing ones. One such example is imbalanced data classification, where, on the one hand, we want to achieve the best…

With the ever-growing size of pretrained models (PMs), fine-tuning them has become more expensive and resource-hungry. As a remedy, low-rank adapters (LoRA) keep the main pretrained weights of the model frozen and just introduce some…

Federated learning (FL) is a promising paradigm to enable collaborative model training with decentralized data. However, the training process of Large Language Models (LLMs) generally incurs the update of significant parameters, which…

The facility location problems (FLPs) are a typical class of NP-hard combinatorial optimization problems, which are widely seen in the supply chain and logistics. Many mathematical and heuristic algorithms have been developed for optimizing…

Pre-trained Language Models (PLMs) have demonstrated their superiority and versatility in modern Natural Language Processing (NLP), effectively adapting to various downstream tasks through further fine-tuning. Federated Parameter-Efficient…

Recent works on parameter-efficient transfer learning (PETL) show the potential to adapt a pre-trained Vision Transformer to downstream recognition tasks with only a few learnable parameters. However, since they usually insert new…