Related papers: Forget Less by Learning from Parents Through Hiera…
We focus on the problem of Personalized Federated Continual Learning (PFCL): a group of distributed clients, each with a sequence of local tasks on arbitrary data distributions, collaborate through a central server to train a personalized…
Catastrophic Forgetting (CF) means models forgetting previously acquired knowledge when learning new data. It compromises the effectiveness of large language models (LLMs) during fine-tuning, yet the underlying causes have not been…
Federated Learning (FL) addresses the need to create models based on proprietary data in such a way that multiple clients retain exclusive control over their data, while all benefit from improved model accuracy due to pooled resources.…
Privacy concerns associated with machine learning models have driven research into machine unlearning, which aims to erase the memory of specific target training data from already trained models. This issue also arises in federated…
Federated Learning (FL) is a distributed machine learning paradigm which coordinates multiple clients to collaboratively train a global model via a central server. Sequential Federated Learning (SFL) is a newly-emerging FL training…
Large Language Models (LLMs) have significantly advanced Natural Language Processing (NLP), particularly in Natural Language Understanding (NLU) tasks. As we progress toward an agentic world where LLM-based agents autonomously handle…
Large language models (LLMs) often require vast amounts of text to effectively acquire new knowledge. While continuing pre-training on large corpora or employing retrieval-augmented generation (RAG) has proven successful, updating an LLM…
With increasing concerns and regulations on data privacy, fine-tuning pretrained language models (PLMs) in federated learning (FL) has become a common paradigm for NLP tasks. Despite being extensively studied, the existing methods for this…
In Federated Learning, a global model is learned by aggregating model updates computed at a set of independent client nodes, to reduce communication costs multiple gradient steps are performed at each node prior to aggregation. A key…
For LLM agents, memory management critically impacts efficiency, quality, and security. While much research focuses on retention, selective forgetting--inspired by human cognitive processes (hippocampal indexing/consolidation theory and…
Machine unlearning is gaining increasing attention as a way to remove adversarial data poisoning attacks from already trained models and to comply with privacy and AI regulations. The objective is to unlearn the effect of undesired data…
In federated learning, a strong global model is collaboratively learned by aggregating clients' locally trained models. Although this precludes the need to access clients' data directly, the global model's convergence often suffers from…
Federated learning (FL) enables privacy-preserving collaborative model training without direct data sharing. Model-heterogeneous FL (MHFL) extends this paradigm by allowing clients to train personalized models with heterogeneous…
Catastrophic forgetting (CF) poses a significant challenge in machine learning, where a model forgets previously learned information upon learning new tasks. Despite the advanced capabilities of Large Language Models (LLMs), they continue…
Pre-trained language models (PLMs) were considered to be able to store relational knowledge present in the training data. However, some relational knowledge seems to be discarded unsafely in PLMs due to \textbf{report bias}: low-frequency…
Few-shot learning is a challenging problem where the goal is to achieve generalization from only few examples. Model-agnostic meta-learning (MAML) tackles the problem by formulating prior knowledge as a common initialization across tasks,…
As Web technology continues to develop, it has become increasingly common to use data stored on different clients. At the same time, federated learning has received widespread attention due to its ability to protect data privacy when let…
Catastrophic forgetting is a significant challenge in continual learning, in which a model loses prior knowledge when it is fine-tuned on new tasks. This problem is particularly critical for large language models (LLMs) undergoing continual…
End-to-end training of Spoken Language Models (SLMs) commonly involves adapting pre-trained text-based Large Language Models (LLMs) to the speech modality through multi-stage training on diverse tasks such as ASR, TTS and spoken question…
Catastrophic forgetting remains a formidable obstacle to building an omniscient model in large language models (LLMs). Despite the pioneering research on task-level forgetting in LLM fine-tuning, there is scant focus on forgetting during…