English
Related papers

Related papers: Orchestrate Latent Expertise: Advancing Online Con…

200 papers

Knowledge distillation is an effective and stable method for model compression via knowledge transfer. Conventional knowledge distillation (KD) is to transfer knowledge from a large and well pre-trained teacher network to a small student…

Computer Vision and Pattern Recognition · Computer Science 2021-11-24 Zhiqiang Liu , Yanxia Liu , Chengkai Huang

Recent breakthroughs in self-supervised learning show that such algorithms learn visual representations that can be transferred better to unseen tasks than joint-training methods relying on task-specific supervision. In this paper, we found…

Machine Learning · Computer Science 2021-06-29 Hyuntak Cha , Jaeho Lee , Jinwoo Shin

Continual learning studies how models can adapt to new tasks while retaining previously acquired knowledge. Although a broad spectrum of methods has been proposed to mitigate catastrophic forgetting, the field remains predominantly…

Machine Learning · Computer Science 2026-05-19 Katarzyna Filus , Kamil Faber , Roberto Corizzo , Christopher Kanan

Continual learning is a process that involves training learning agents to sequentially master a stream of tasks or classes without revisiting past data. The challenge lies in leveraging previously acquired knowledge to learn new tasks…

Machine Learning · Computer Science 2024-02-21 Marcus de Carvalho , Mahardhika Pratama , Jie Zhang , Chua Haoyan , Edward Yapp

We present a novel class incremental learning approach based on deep neural networks, which continually learns new tasks with limited memory for storing examples in the previous tasks. Our algorithm is based on knowledge distillation and…

Machine Learning · Computer Science 2022-04-05 Minsoo Kang , Jaeyoo Park , Bohyung Han

Humans have a remarkable ability to quickly and effectively learn new concepts in a continuous manner without forgetting old knowledge. Though deep learning has made tremendous successes on various computer vision tasks, it faces challenges…

Machine Learning · Computer Science 2022-07-26 Kun Wu , Chengxiang Yin , Jian Tang , Zhiyuan Xu , Yanzhi Wang , Dejun Yang

The continuous changes in the world have resulted in the performance regression of neural networks. Therefore, continual learning (CL) area gradually attracts the attention of more researchers. For edge intelligence, the CL model not only…

Machine Learning · Computer Science 2023-03-22 Xiangwei Wang , Rui Han , Chi Harold Liu

We address the problem of self-supervised learning on discrete event sequences generated by real-world users. Self-supervised learning incorporates complex information from the raw data in low-dimensional fixed-length vector representations…

Machine Learning · Computer Science 2022-07-25 Dmitrii Babaev , Ivan Kireev , Nikita Ovsov , Mariya Ivanova , Gleb Gusev , Ivan Nazarov , Alexander Tuzhilin

Continual learning (CL) aims to empower models to learn new tasks without forgetting previously acquired knowledge. Most prior works concentrate on the techniques of architectures, replay data, regularization, \etc. However, the category…

Computer Vision and Pattern Recognition · Computer Science 2024-03-26 Bolin Ni , Hongbo Zhao , Chenghao Zhang , Ke Hu , Gaofeng Meng , Zhaoxiang Zhang , Shiming Xiang

In continual learning (CL), a learner is faced with a sequence of tasks, arriving one after the other, and the goal is to remember all the tasks once the continual learning experience is finished. The prior art in CL uses episodic memory,…

Machine Learning · Computer Science 2020-12-09 Arslan Chaudhry , Naeemullah Khan , Puneet K. Dokania , Philip H. S. Torr

Multimodal Large Language Models (MLLMs) achieve strong performance through instruction tuning, but real-world deployment requires them to continually expand their capabilities, making Multimodal Continual Instruction Tuning (MCIT)…

Machine Learning · Computer Science 2026-05-28 Zhen-Hao Xie , Jun-Tao Tang , Yu-Cheng Shi , Han-Jia Ye , De-Chuan Zhan , Da-Wei Zhou

In Continual learning (CL) balancing effective adaptation while combating catastrophic forgetting is a central challenge. Many of the recent best-performing methods utilize various forms of prior task data, e.g. a replay buffer, to tackle…

Machine Learning · Computer Science 2023-06-07 Nader Asadi , MohammadReza Davari , Sudhir Mudur , Rahaf Aljundi , Eugene Belilovsky

Online continual learning (OCL) methods adapt to changing environments without forgetting past knowledge. Similarly, online time series forecasting (OTSF) is a real-world problem where data evolve in time and success depends on both rapid…

Machine Learning · Computer Science 2026-01-21 Edoardo Urettini , Daniele Atzeni , Ioanna-Yvonni Tsaknaki , Antonio Carta

An ultimate objective in continual learning is to preserve knowledge learned in preceding tasks while learning new tasks. To mitigate forgetting prior knowledge, we propose a novel knowledge distillation technique that takes into the…

Computer Vision and Pattern Recognition · Computer Science 2023-08-02 Kaushik Roy , Christian Simon , Peyman Moghadam , Mehrtash Harandi

While deep learning has achieved remarkable results on various applications, it is usually data hungry and struggles to learn over non-stationary data stream. To solve these two limits, the deep learning model should not only be able to…

Machine Learning · Computer Science 2019-09-05 Canyu Le , Xihan Wei , Biao Wang , Lei Zhang , Zhonggui Chen

Catastrophic forgetting is a significant challenge in online continual learning (OCL), especially for non-stationary data streams that do not have well-defined task boundaries. This challenge is exacerbated by the memory constraints and…

Computer Vision and Pattern Recognition · Computer Science 2024-11-11 Xiwen Wei , Guihong Li , Radu Marculescu

We formulate a unifying framework for unsupervised continual learning (UCL), which disentangles learning objectives that are specific to the present and the past data, encompassing stability, plasticity, and cross-task consolidation. The…

Machine Learning · Computer Science 2024-08-13 Yipeng Zhang , Laurent Charlin , Richard Zemel , Mengye Ren

Contrastive Learning (CL) performances as a rising approach to address the challenge of sparse and noisy recommendation data. Although having achieved promising results, most existing CL methods only perform either hand-crafted data or…

Information Retrieval · Computer Science 2023-11-22 Xiuyuan Qin , Huanhuan Yuan , Pengpeng Zhao , Junhua Fang , Fuzhen Zhuang , Guanfeng Liu , Victor Sheng

Deep Learning (DL) requires lots of time and data, resulting in high computational demands. Recently, researchers employ Active Learning (AL) and online distillation to enhance training efficiency and real-time model adaptation. This paper…

Computer Vision and Pattern Recognition · Computer Science 2023-09-06 Michele Boldo , Enrico Martini , Mirco De Marchi , Stefano Aldegheri , Nicola Bombieri

Human education system trains one student by multiple experts. Mixture-of-experts (MoE) is a powerful sparse architecture including multiple experts. However, sparse MoE model is easy to overfit, hard to deploy, and not hardware-friendly…

Machine Learning · Computer Science 2022-10-26 Fuzhao Xue , Xiaoxin He , Xiaozhe Ren , Yuxuan Lou , Yang You