Related papers: A distillation-based approach integrating continua…

Catastrophic forgetting has been a significant problem hindering the deployment of deep learning algorithms in the continual learning setting. Numerous methods have been proposed to address the catastrophic forgetting problem where an agent…

The ongoing deployment of the Internet of Things (IoT)-based smart applications is spurring the adoption of machine learning as a key technology enabler. To overcome the privacy and overhead challenges of centralized machine learning, there…

Federated Learning is a novel framework that allows multiple devices or institutions to train a machine learning model collaboratively while preserving their data private. This decentralized approach is prone to suffer the consequences of…

In real-world applications, Federated Learning (FL) meets two challenges: (1) scalability, especially when applied to massive IoT networks; and (2) how to be robust against an environment with heterogeneous data. Realizing the first…

We propose a novel approach for class incremental online learning in a limited data setting. This problem setting is challenging because of the following constraints: (1) Classes are given incrementally, which necessitates a class…

Federated learning involves training statistical models over remote devices or siloed data centers, such as mobile phones or hospitals, while keeping data localized. Training in heterogeneous and potentially massive networks introduces…

Federated learning has emerged as a promising approach for training machine learning models on decentralized data sources while preserving data privacy. However, challenges such as communication bottlenecks, heterogeneity of client devices,…

Over the past few years, significant advancements have been made in the field of machine learning (ML) to address resource management, interference management, autonomy, and decision-making in wireless networks. Traditional ML approaches…

Human Activity Recognition is an important task in many human-computer collaborative scenarios, whilst having various practical applications. Although uni-modal approaches have been extensively studied, they suffer from data quality and…

This paper focuses on an under-explored yet important problem: Federated Class-Continual Learning (FCCL), where new classes are dynamically added in federated learning. Existing FCCL works suffer from various limitations, such as requiring…

Learning from the collective knowledge of data dispersed across private sources can provide neural networks with enhanced generalization capabilities. Federated learning, a method for collaboratively training a machine learning model across…

Video representation learning is a vital problem for classification task. Recently, a promising unsupervised paradigm termed self-supervised learning has emerged, which explores inherent supervisory signals implied in massive data for…

Dataset distillation aims to condense large datasets into a small number of synthetic examples that can be used as drop-in replacements when training new models. It has applications to interpretability, neural architecture search, privacy,…

Federated learning (FL) is increasingly being recognized as a key approach to overcoming the data silos that so frequently obstruct the training and deployment of machine-learning models in clinical settings. This work contributes to a…

Instance-incremental learning (IIL) focuses on learning continually with data of the same classes. Compared to class-incremental learning (CIL), the IIL is seldom explored because IIL suffers less from catastrophic forgetting (CF). However,…

Active learning can be defined as iterations of data labeling, model training, and data acquisition, until sufficient labels are acquired. A traditional view of data acquisition is that, through iterations, knowledge from human labels and…

Federated learning is a renowned technique for utilizing decentralized data while preserving privacy. However, real-world applications often face challenges like partially labeled datasets, where only a few locations have certain expert…

Wearable sensor-based human activity recognition (HAR) has emerged as a principal research area and is utilized in a variety of applications. Recently, deep learning-based methods have achieved significant improvement in the HAR field with…

Federated Learning (FL) is a privacy-constrained decentralized machine learning paradigm in which clients enable collaborative training without compromising private data. However, how to learn a robust global model in the data-heterogeneous…

Human intelligence is characterized not only by the capacity to learn complex skills, but the ability to rapidly adapt and acquire new skills within an ever-changing environment. In this work we study how the learning of modular solutions…