English
Related papers

Related papers: Supermasks in Superposition

200 papers

Catastrophic forgetting occurs when a neural network loses the information learned in a previous task after training on subsequent tasks. This problem remains a hurdle for artificial intelligence systems with sequential learning…

Machine Learning · Computer Science 2018-05-30 Joan Serrà , Dídac Surís , Marius Miron , Alexandros Karatzoglou

Multitask algorithms typically use task similarity information as a bias to speed up and improve the performance of learning processes. Tasks are learned jointly, sharing information across them, in order to construct models more accurate…

Machine Learning · Computer Science 2019-04-11 Marco Frasca , Giuliano Grossi , Giorgio Valentini

Self-supervised learning (SSL), as a newly emerging unsupervised representation learning paradigm, generally follows a two-stage learning pipeline: 1) learning invariant and discriminative representations with auto-annotation pretext(s),…

Machine Learning · Computer Science 2022-08-23 Jiayu Yao , Qingyuan Wu , Quan Feng , Songcan Chen

This paper proposes a novel approach to pattern classification using a probabilistic neural network model. The strategy is based on a compact-sized probabilistic neural network capable of continuous incremental learning and unlearning…

Machine Learning · Computer Science 2026-03-24 Tetsuya Hoya , Shunpei Morita

Self-supervised learning approaches leverage unlabeled samples to acquire generic knowledge about different concepts, hence allowing for annotation-efficient downstream task learning. In this paper, we propose a novel self-supervised method…

Computer Vision and Pattern Recognition · Computer Science 2020-10-27 Aiham Taleb , Christoph Lippert , Tassilo Klein , Moin Nabi

Ensembling a neural network is a widely recognized approach to enhance model performance, estimate uncertainty, and improve robustness in deep supervised learning. However, deep ensembles often come with high computational costs and memory…

Model merging enables powerful capabilities in neural networks without requiring additional training. In this paper, we introduce a novel perspective on model merging by leveraging the fundamental mechanisms of neural network…

Machine Learning · Computer Science 2025-09-19 Haiquan Qiu , You Wu , Dong Li , Jianmin Guo , Quanming Yao

Recently, anomaly detection and localization in multimedia data have received significant attention among the machine learning community. In real-world applications such as medical diagnosis and industrial defect detection, anomalies only…

Computer Vision and Pattern Recognition · Computer Science 2022-05-16 Chaoqin Huang , Qinwei Xu , Yanfeng Wang , Yu Wang , Ya Zhang

Artificial neural networks thrive in solving the classification problem for a particular rigid task, acquiring knowledge through generalized learning behaviour from a distinct training phase. The resulting network resembles a static entity…

Computer Vision and Pattern Recognition · Computer Science 2021-04-19 Matthias De Lange , Rahaf Aljundi , Marc Masana , Sarah Parisot , Xu Jia , Ales Leonardis , Gregory Slabaugh , Tinne Tuytelaars

Sequential recommendation aims to provide users with personalized suggestions based on their historical interactions. When training sequential models, padding is a widely adopted technique for two main reasons: 1) The vast majority of…

Information Retrieval · Computer Science 2025-07-16 Yizhou Dang , Yuting Liu , Enneng Yang , Guibing Guo , Linying Jiang , Jianzhe Zhao , Xingwei Wang

We investigate methods for combining multiple self-supervised tasks--i.e., supervised tasks where data can be collected without manual labeling--in order to train a single visual representation. First, we provide an apples-to-apples…

Computer Vision and Pattern Recognition · Computer Science 2017-08-29 Carl Doersch , Andrew Zisserman

We propose an approach without any forgetting to continual learning for the task-aware regime, where at inference the task-label is known. By using ternary masks we can upgrade a model to new tasks, reusing knowledge from previous tasks…

Computer Vision and Pattern Recognition · Computer Science 2021-04-22 Marc Masana , Tinne Tuytelaars , Joost van de Weijer

The Cambrian explosion of easily accessible pre-trained diffusion models suggests a demand for methods that combine multiple different pre-trained diffusion models without incurring the significant computational burden of re-training a…

Machine Learning · Computer Science 2025-03-04 Marta Skreta , Lazar Atanackovic , Avishek Joey Bose , Alexander Tong , Kirill Neklyudov

Pre-training large neural networks at scale imposes heavy memory demands on accelerators and often requires costly communication. We introduce Subnetwork Data Parallelism (SDP), a distributed training framework that partitions a model into…

Machine Learning · Computer Science 2025-10-06 Vaibhav Singh , Zafir Khalid , Edouard Oyallon , Eugene Belilovsky

Neural networks achieve remarkable performance through superposition: encoding multiple features as overlapping directions in activation space rather than dedicating individual neurons to each feature. This challenges interpretability, yet…

Machine Learning · Computer Science 2025-12-16 Leonard Bereska , Zoe Tzifa-Kratira , Reza Samavi , Efstratios Gavves

Deep models are designed to operate on huge volumes of high dimensional data such as images. In order to reduce the volume of data these models must process, we propose a set-based two-stage end-to-end neural subsampling model that is…

Machine Learning · Computer Science 2022-05-31 Bruno Andreis , Seanie Lee , A. Tuan Nguyen , Juho Lee , Eunho Yang , Sung Ju Hwang

The Hopfield recurrent neural network is a classical auto-associative model of memory, in which collections of symmetrically-coupled McCulloch-Pitts neurons interact to perform emergent computation. Although previous researchers have…

Adaptation and Self-Organizing Systems · Physics 2015-06-09 Christopher Hillar , Ngoc M. Tran

In many sequential tasks, a model needs to remember relevant events from the distant past to make correct predictions. Unfortunately, a straightforward application of gradient based training requires intermediate computations to be stored…

Machine Learning · Computer Science 2023-08-14 Artyom Sorokin , Nazar Buzun , Leonid Pugachev , Mikhail Burtsev

Unsupervised learning methods based on contrastive learning have drawn increasing attention and achieved promising results. Most of them aim to learn representations invariant to instance-level variations, which are provided by different…

Computer Vision and Pattern Recognition · Computer Science 2020-11-04 Feng Wang , Huaping Liu , Di Guo , Fuchun Sun

Self-supervised learning aims to learn good representations with unlabeled data. Recent works have shown that larger models benefit more from self-supervised learning than smaller models. As a result, the gap between supervised and…

Computer Vision and Pattern Recognition · Computer Science 2020-10-29 Soroush Abbasi Koohpayegani , Ajinkya Tejankar , Hamed Pirsiavash