English
Related papers

Related papers: Towards Redundancy-Free Sub-networks in Continual …

200 papers

Continual/lifelong learning from a non-stationary input data stream is a cornerstone of intelligence. Despite their phenomenal performance in a wide variety of applications, deep neural networks are prone to forgetting their previously…

Machine Learning · Computer Science 2022-07-11 Ali Abbasi , Parsa Nooralinejad , Vladimir Braverman , Hamed Pirsiavash , Soheil Kolouri

Existing Continual Learning (CL) approaches have focused on addressing catastrophic forgetting by leveraging regularization methods, replay buffers, and task-specific components. However, realistic CL solutions must be shaped not only by…

Machine Learning · Computer Science 2023-10-11 Jinyung Hong , Theodore P. Pavlic

We propose incremental (re)training of a neural network model to cope with a continuous flow of new data in inference during model serving. As such, this is a life-long learning process. We address two challenges of life-long retraining:…

Machine Learning · Computer Science 2020-04-30 Diego Klabjan , Xiaofeng Zhu

Despite remarkable successes achieved by modern neural networks in a wide range of applications, these networks perform best in domain-specific stationary environments where they are trained only once on large-scale controlled data…

Neural and Evolutionary Computing · Computer Science 2019-04-23 Pouya Bashivan , Martin Schrimpf , Robert Ajemian , Irina Rish , Matthew Riemer , Yuhai Tu

Residual networks (ResNet) and weight normalization play an important role in various deep learning applications. However, parameter initialization strategies have not been studied previously for weight normalized networks and, in practice,…

Machine Learning · Statistics 2019-10-31 Devansh Arpit , Victor Campos , Yoshua Bengio

Explaining the behaviors of deep neural networks, usually considered as black boxes, is critical especially when they are now being adopted over diverse aspects of human life. Taking the advantages of interpretable machine learning…

Machine Learning · Computer Science 2022-07-26 Giang Nguyen , Shuan Chen , Tae Joon Jun , Daeyoung Kim

Adapting pretrained large language models (LLMs) to code domains via supervised fine-tuning (FT) has been commonly used for code generation. However, we identify a previously underappreciated failure mode, the memorization barrier, where…

Machine Learning · Computer Science 2025-10-21 Changsheng Wang , Xin Chen , Sijia Liu , Ke Ding

Lifelong learning is a very important step toward realizing robust autonomous artificial agents. Neural networks are the main engine of deep learning, which is the current state-of-the-art technique in formulating adaptive artificial…

Machine Learning · Computer Science 2019-12-11 Mohammed Amer , Tomás Maul

Neural Fields (NF) have gained prominence as a versatile framework for complex data representation. This work unveils a new problem setting termed \emph{Meta-Continual Learning of Neural Fields} (MCL-NF) and introduces a novel strategy that…

Artificial Intelligence · Computer Science 2026-02-24 Seungyoon Woo , Junhyeog Yun , Gunhee Kim

Concept Bottleneck Models (CBMs) map the black-box visual representations extracted by deep neural networks onto a set of interpretable concepts and use the concepts to make predictions, enhancing the transparency of the decision-making…

Machine Learning · Computer Science 2024-04-18 Chenming Shang , Shiji Zhou , Hengyuan Zhang , Xinzhe Ni , Yujiu Yang , Yuwang Wang

Continual learning (CL) aims to extend deep models from static and enclosed environments to dynamic and complex scenarios, enabling systems to continuously acquire new knowledge of novel categories without forgetting previously learned…

Computer Vision and Pattern Recognition · Computer Science 2024-05-21 Sunyuan Qiang , Xuxin Lin , Yanyan Liang , Jun Wan , Du Zhang

Recently, a new Continual Learning (CL) paradigm was presented to control catastrophic forgetting, called Interval Continual Learning (InterContiNet), which relies on enforcing interval constraints on the neural network parameter space.…

Machine Learning · Computer Science 2025-05-07 Patryk Krukowski , Anna Bielawska , Kamil Książek , Paweł Wawrzyński , Paweł Batorski , Przemysław Spurek

Typical dimensionality reduction methods focus on directly reducing the number of random variables while retaining maximal variations in the data. In this paper, we consider the dimensionality reduction in parameter spaces of binary…

Neural and Evolutionary Computing · Computer Science 2013-10-10 Xiaozhao Zhao , Yuexian Hou , Qian Yu , Dawei Song , Wenjie Li

Federated Learning (FL) plays a critical role in distributed systems. In these systems, data privacy and confidentiality hold paramount importance, particularly within edge-based data processing systems such as IoT devices deployed in smart…

Machine Learning · Computer Science 2024-03-08 Humaid Ahmed Desai , Amr Hilal , Hoda Eldardiry

Normalization is fundamental to deep learning, but existing approaches such as BatchNorm, LayerNorm, and RMSNorm are variance-centric by enforcing zero mean and unit variance, stabilizing training without controlling how representations…

Machine Learning · Computer Science 2026-01-30 Xiandong Zou , Jia Li , Xiaotong Yuan , Pan Zhou

Continual learning (CL) is a setting in which an agent has to learn from an incoming stream of data during its entire lifetime. Although major advances have been made in the field, one recurring problem which remains unsolved is that of…

Machine Learning · Computer Science 2021-02-26 Thang Doan , Mehdi Bennani , Bogdan Mazoure , Guillaume Rabusseau , Pierre Alquier

Deep neural networks with short residual connections have demonstrated remarkable success across domains, but increasing depth often introduces computational redundancy without corresponding improvements in representation quality. We…

Machine Learning · Computer Science 2025-11-10 Vaggelis Dorovatas , Georgios Paraskevopoulos , Alexandros Potamianos

Continual learning (CL) is essential for Large Language Models (LLMs) to adapt to evolving real-world demands, yet they are susceptible to catastrophic forgetting (CF). While traditional CF solutions rely on expensive data rehearsal, recent…

Machine Learning · Computer Science 2025-02-18 Huanxuan Liao , Shizhu He , Yupu Hao , Jun Zhao , Kang Liu

Recent research has shown the existence of significant redundancy in large Transformer models. One can prune the redundant parameters without significantly sacrificing the generalization performance. However, we question whether the…

Computation and Language · Computer Science 2022-02-15 Chen Liang , Haoming Jiang , Simiao Zuo , Pengcheng He , Xiaodong Liu , Jianfeng Gao , Weizhu Chen , Tuo Zhao

Current training regimes for deep learning usually involve exposure to a single task / dataset at a time. Here we start from the observation that in this context the trained model is not given any knowledge of anything outside its…

Artificial Intelligence · Computer Science 2020-02-11 Giacomo Spigler