paper-with-me

홈 › Papers

Exploring Kolmogorov-Arnold Network Expansions in Vision Transformers for Mitigating Catastrophic Forgetting in Continual Learning

2025-07-05 · Zahid Ullah, Jihie Kim arxiv

Continual learning (CL), the ability of a model to learn new tasks without forgetting previously acquired knowledge, remains a critical challenge in artificial intelligence, particularly for vision transformers (ViTs) utilizing Multilayer Perceptrons (MLPs) for global representation learning. Catastrophic forgetting, where new information overwrites prior knowledge, is especially problematic in these models. This research proposes replacing MLPs in ViTs with Kolmogorov-Arnold Network (KANs) to address this issue. KANs leverage local plasticity through spline-based activations, ensuring that only a subset of parameters is updated per sample, thereby preserving previously learned knowledge. The study investigates the efficacy of KAN-based ViTs in CL scenarios across benchmark datasets (MNIST, CIFAR100), focusing on their ability to retain accuracy on earlier tasks while adapting to new ones. Experimental results demonstrate that KAN-based ViTs significantly mitigate catastrophic forgetting, outperforming traditional MLP-based ViTs in knowledge retention and task adaptation. This novel integration of KANs into ViTs represents a promising step toward more robust and adaptable models for dynamic environments.

📄 PDF Abstract BibTeX arXiv:2507.04020

Code (0)

등록된 구현이 없습니다.

Tasks

Representation LearningContinual Learning

Similar Papers 제목 키워드 기반

ViKANformer: Embedding Kolmogorov Arnold Networks in Vision Transformers for Pattern-Based Learning

2025-03-03 · Shreyas S, Akshath M

Vision Transformers (ViTs) have significantly advanced image classification by applying self-attention on patch embeddings. However, the standard MLP blocks in each Transformer layer may not capture complex nonlinear dep…

image-classificationImage ClassificationKolmogorov-Arnold Networks

Kolmogorov-Arnold Reservoir Computing

2026-06-18 · Juntian Huang, Jürgen Kurths, Ying Tang arxiv

Reservoir computing offers a lightweight framework for forecasting dynamical systems but may struggle to capture long-range dependencies due to limited representational capacity. Conventional reservoir computing recurren…

Text-to-Image Generation

"KAN you hear me?" Exploring Kolmogorov-Arnold Networks for Spoken Language Understanding

2025-05-26 · Alkis Koudounas, Moreno La Quatra, Eliana Pastor, Sabato Marco Siniscalchi 외

Kolmogorov-Arnold Networks (KANs) have recently emerged as a promising alternative to traditional neural architectures, yet their application to speech processing remains under explored. This work presents the first inve…

Kolmogorov-Arnold NetworksSpoken Language Understanding

A Temporal Kolmogorov-Arnold Transformer for Time Series Forecasting

2024-06-04 · Remi Genet, Hugo Inzirillo

Capturing complex temporal patterns and relationships within multivariate data streams is a difficult task. We propose the Temporal Kolmogorov-Arnold Transformer (TKAT), a novel attention-based architecture designed to a…

DecoderKolmogorov-Arnold NetworksTime SeriesTime Series Forecasting

Can KAN Work? Exploring the Potential of Kolmogorov-Arnold Networks in Computer Vision

2024-11-11 · Yueyang Cang, Yu hang liu, Li Shi

Kolmogorov-Arnold Networks(KANs), as a theoretically efficient neural network architecture, have garnered attention for their potential in capturing complex patterns. However, their application in computer vision remains…

Efficient Neural Networkimage-classificationImage ClassificationKolmogorov-Arnold Networks+1