中文
相关论文

相关论文: Catastrophic Forgetting in Kolmogorov-Arnold Netwo…

200 篇论文

Benefiting from massive corpora and advanced hardware, large language models (LLMs) exhibit remarkable capabilities in language understanding and generation. However, their performance degrades in scenarios where multiple tasks are…

计算与语言 · 计算机科学 2023-10-24 Xiao Wang , Tianze Chen , Qiming Ge , Han Xia , Rong Bao , Rui Zheng , Qi Zhang , Tao Gui , Xuanjing Huang

Kolmogorov-Arnold networks (KANs) as an alternative to multi-layer perceptrons (MLPs) are a recent development demonstrating strong potential for data-driven modeling. This work applies KANs as the backbone of a neural ordinary differential…

机器学习 · 计算机科学 2024-09-23 Benjamin C. Koenig , Suyong Kim , Sili Deng

Large language models exhibit remarkable performance across diverse tasks through pre-training and fine-tuning paradigms. However, continual fine-tuning on sequential tasks induces catastrophic forgetting, where newly acquired knowledge…

机器学习 · 计算机科学 2026-01-27 Olaf Yunus Laitinen Imanov

Neural networks have been criticised for their inability to perform continual learning due to catastrophic forgetting and rapid unlearning of a past concept when a new concept is introduced. Catastrophic forgetting can be alleviated by…

机器学习 · 计算机科学 2022-05-16 Heinrich van Deventer , Pieter Janse van Rensburg , Anna Bosman

A primary focus area in continual learning research is alleviating the "catastrophic forgetting" problem in neural networks by designing new algorithms that are more robust to the distribution shifts. While the recent progress in continual…

机器学习 · 计算机科学 2022-07-15 Seyed Iman Mirzadeh , Arslan Chaudhry , Dong Yin , Huiyi Hu , Razvan Pascanu , Dilan Gorur , Mehrdad Farajtabar

Learning a set of tasks over time, also known as continual learning (CL), is one of the most challenging problems in artificial intelligence due to catastrophic forgetting. Large language models (LLMs) are often impractical to frequent…

机器学习 · 计算机科学 2025-10-28 Jaya Krishna Mandivarapu

Kolmogorov-Arnold Networks have recently been introduced as a flexible alternative to multi-layer Perceptron architectures. In this paper, we examine the training dynamics of different KAN architectures and compare them with corresponding…

机器学习 · 计算机科学 2024-11-11 Shairoz Sohail

By utilising their adaptive activation functions, Kolmogorov-Arnold Networks (KANs) can be applied in a novel way for the diverse machine learning tasks, including cyber threat detection. KANs substitute conventional linear weights with…

密码学与安全 · 计算机科学 2026-04-01 Mohammed Hassanin

Building learning agents that can progressively learn and accumulate knowledge is the core goal of the continual learning (CL) research field. Unfortunately, training a model on new data usually compromises the performance on past data. In…

Continual lifelong learning requires an agent or model to learn many sequentially ordered tasks, building on previous knowledge without catastrophically forgetting it. Much work has gone towards preventing the default tendency of machine…

机器学习 · 计算机科学 2020-03-05 Shawn Beaulieu , Lapo Frati , Thomas Miconi , Joel Lehman , Kenneth O. Stanley , Jeff Clune , Nick Cheney

Continual learning refers to the problem where the training data is available in sequential chunks, termed "tasks". The majority of progress in continual learning has been stunted by the problem of catastrophic forgetting, which is caused…

计算机视觉与模式识别 · 计算机科学 2023-11-07 Rajas Chitale , Ankit Vaidya , Aditya Kane , Archana Ghotkar

Recently, Kolmogorov-Arnold Networks (KANs) have been proposed as an alternative to multilayer perceptrons, suggesting advantages in performance and interpretability. We study a typical binary event classification task in high-energy…

高能物理 - 唯象学 · 物理学 2025-05-27 Johannes Erdmann , Florian Mausolf , Jan Lukas Späh

In this paper, we show that Generative Adversarial Networks (GANs) suffer from catastrophic forgetting even when they are trained to approximate a single target distribution. We show that GAN training is a continual learning problem in…

机器学习 · 计算机科学 2020-03-24 Hoang Thanh-Tung , Truyen Tran

Fine-tuning large language models (LLMs) with Low-Rank adaption (LoRA) is widely acknowledged as an effective approach for continual learning for new tasks. However, it often suffers from catastrophic forgetting when dealing with multiple…

计算与语言 · 计算机科学 2024-10-01 Jialin Liu , Jianhua Wu , Jie Liu , Yutai Duan

Continual learning on sequential data is critical for many machine learning (ML) deployments. Unfortunately, LSTM networks, which are commonly used to learn on sequential data, suffer from catastrophic forgetting and are limited in their…

机器学习 · 计算机科学 2023-05-30 Ketaki Joshi , Raghavendra Pradyumna Pothukuchi , Andre Wibisono , Abhishek Bhattacharjee

A common challenge in continual learning (CL) is catastrophic forgetting, where the performance on old tasks drops after new, additional tasks are learned. In this paper, we propose a novel framework called ReCL to slow down forgetting in…

机器学习 · 计算机科学 2025-03-04 Pascal Janetzky , Tobias Schlagenhauf , Stefan Feuerriegel

Human being and different species of animals having the skills to gather, transferring knowledge, processing, fine-tune and generating information throughout their lifetime. The ability of learning throughout their lifespan is referred as…

机器学习 · 计算机科学 2024-05-15 Ashutosh Kumar , Sonali Agarwal , D Jude Hemanth

Continual learning requires models to train continuously across consecutive tasks without forgetting. Most existing methods utilize linear classifiers, which struggle to maintain a stable classification space while learning new tasks.…

计算机视觉与模式识别 · 计算机科学 2025-03-28 Yusong Hu , Zichen Liang , Fei Yang , Qibin Hou , Xialei Liu , Ming-Ming Cheng

The recently proposed Kolmogorov-Arnold network (KAN) is a promising alternative to multi-layer perceptrons (MLPs) for data-driven modeling. While original KAN layers were only capable of representing the addition operator, the…

机器学习 · 计算机科学 2025-07-28 Benjamin C. Koenig , Suyong Kim , Sili Deng

We study the issue of catastrophic forgetting in the context of neural multimodal approaches to Visual Question Answering (VQA). Motivated by evidence from psycholinguistics, we devise a set of linguistically-informed VQA tasks, which…

计算与语言 · 计算机科学 2019-06-12 Claudio Greco , Barbara Plank , Raquel Fernández , Raffaella Bernardi