paper-with-me

Papers

Task agnostic continual learning with Pairwise layer architecture

2024-05-22 · Santtu Keskinen

Most of the dominant approaches to continual learning are based on either memory replay, parameter isolation, or regularization techniques that require task boundaries to calculate task statistics. We propose a static architecture-based method that doesn't use any of these. We show that we can improve the continual learning performance by replacing the final layer of our networks with our pairwise interaction layer. The pairwise interaction layer uses sparse representations from a Winner-take-all style activation function to find the relevant correlations in the hidden layer representations. The networks using this architecture show competitive performance in MNIST and FashionMNIST-based continual image classification experiments. We demonstrate this in an online streaming continual learning setup where the learning system cannot access task labels or boundaries.

📄 PDF Abstract BibTeX arXiv:2405.13632

Code (1)

skeskinen/pairwise_online_learning 공식 구현 jax

Tasks

Continual Learningimage-classificationImage Classification

Similar Papers 제목 키워드 기반

Causally-Guided Pairwise Transformer -- Towards Foundational Digital Twins in Process Industry

2025-08-18 · Michael Mayr, Georgios C. Chasparis arxiv

Foundational modelling of multi-dimensional time-series data in industrial systems presents a central trade-off: channel-dependent (CD) models capture specific cross-variable dynamics but lack robustness and adaptability…

Hierarchically Structured Task-Agnostic Continual Learning

2022-11-14 · Heinke Hihn, Daniel A. Braun

One notable weakness of current machine learning algorithms is the poor ability of models to solve new problems without forgetting previously acquired knowledge. The Continual Learning paradigm has emerged as a protocol …

Continual Learningreinforcement-learningReinforcement Learning (RL)

Dynamic Mixture of Curriculum LoRA Experts for Continual Multimodal Instruction Tuning

2025-06-13 · Chendi Ge, Xin Wang, Zeyang Zhang, Hong Chen 외

Continual multimodal instruction tuning is crucial for adapting Multimodal Large Language Models (MLLMs) to evolving tasks. However, most existing methods adopt a fixed architecture, struggling with adapting to new tasks…

Continual Learning

Task Agnostic Continual Learning Using Online Variational Bayes with Fixed-Point Updates

2020-10-01 · Chen Zeno, Itay Golan, Elad Hoffer, Daniel Soudry

Background: Catastrophic forgetting is the notorious vulnerability of neural networks to the changes in the data distribution during learning. This phenomenon has long been considered a major obstacle for using learning …

Continual Learning

Explainable Lifelong Stream Learning Based on "Glocal" Pairwise Fusion

2023-06-23 · Chu Kiong Loo, Wei Shiung Liew, Stefan Wermter

Real-time on-device continual learning applications are used on mobile phones, consumer robots, and smart appliances. Such devices have limited processing and memory storage capabilities, whereas continual learning acqui…

Continual LearningLifelong learning