Related papers: Forget Less by Learning from Parents Through Hiera…

Cross-silo federated learning (FL) enables decentralized organizations to collaboratively train models while preserving data privacy and has made significant progress in medical image classification. One common assumption is task…

Class-incremental learning (CIL) has achieved remarkable successes in learning new classes consecutively while overcoming catastrophic forgetting on old categories. However, most existing CIL methods unreasonably assume that all old…

Federated learning (FL) allows collaborative machine learning training without sharing private data. While most FL methods assume identical data domains across clients, real-world scenarios often involve heterogeneous data domains.…

The increasing size of data generated by smartphones and IoT devices motivated the development of Federated Learning (FL), a framework for on-device collaborative training of machine learning models. First efforts in FL focused on learning…

Cross-capability transfer is a key challenge in large language model (LLM) research, with applications in multi-task integration, model compression, and continual learning. Recent works like FuseLLM and FuseChat have demonstrated the…

Federated learning (FL) is a distributed learning method that offers medical institutes the prospect of collaboration in a global model while preserving the privacy of their patients. Although most medical centers conduct similar medical…

Catastrophic forgetting (CF) is a phenomenon that occurs in machine learning when a model forgets previously learned information while acquiring new knowledge for achieving a satisfactory performance in downstream tasks. As large language…

Collaborative filtering (CF) remains essential in recommender systems, leveraging user--item interactions to provide personalized recommendations. Meanwhile, a number of CF techniques have evolved into sophisticated model architectures…

Recent advancements in Large Language Models (LLMs) have showcased their remarkable capabilities in text understanding and generation. However, even stronger LLMs are susceptible to acquiring erroneous or obsolete information from the…

Federated Learning (FL) has emerged as a promising solution in Edge Computing (EC) environments to process the proliferation of data generated by edge devices. By collaboratively optimizing the global machine learning models on distributed…

Despite the increasing prevalence of large language models (LLMs), we still have a limited understanding of how their representational spaces are structured. This limits our ability to interpret how and what they learn or relate them to…

Recently, the pretrain-finetune paradigm has become a cornerstone in various deep learning areas. While in general the pre-trained model would promote both effectiveness and efficiency of downstream tasks fine-tuning, studies have shown…

Text-to-image (T2I) diffusion models have achieved remarkable success in generating high-quality images from textual prompts. However, their ability to store vast amounts of knowledge raises concerns in scenarios where selective forgetting…

In recent years, deep neural networks have significantly impacted the seismic interpretation process. Due to the simple implementation and low interpretation costs, deep neural networks are an attractive component for the common…

Although many efforts have been made, it is still a challenge to balance the training budget, downstream performance, and the general capabilities of the LLMs in many applications. Training the whole model for downstream tasks is expensive,…

The recent proliferation of large-scale text-to-image models has led to growing concerns that such models may be misused to generate harmful, misleading, and inappropriate content. Motivated by this issue, we derive a technique inspired by…

Catastrophic forgetting remains a fundamental challenge in continual learning, in which models often forget previous knowledge when fine-tuned on a new task. This issue is especially pronounced in class incremental learning (CIL), which is…

Recent works have shown that generative sequence models (e.g., language models) have a tendency to memorize rare or unique sequences in the training data. Since useful models are often trained on sensitive data, to ensure the privacy of the…

Learning from changing tasks and sequential experience without forgetting the obtained knowledge is a challenging problem for artificial neural networks. In this work, we focus on two challenging problems in the paradigm of Continual…

Pre-trained Vision-Language Models (VLMs) require Continual Learning (CL) to efficiently update their knowledge and adapt to various downstream tasks without retraining from scratch. However, for VLMs, in addition to the loss of knowledge…