Test-time adaptation is a promising research direction that allows the s...
In this work, we improve the generative replay in a continual learning
s...
Federated Learning (FL) has emerged as a key approach for distributed ma...
Continuous unsupervised representation learning (CURL) research has grea...
In this work, we investigate exemplar-free class incremental learning (C...
In modern e-commerce, item content features in various modalities offer
...
Continual learning enables incremental learning of new tasks without
for...
Multi-domain recommender systems benefit from cross-domain representatio...
In Federated Learning (FL) of click-through rate (CTR) prediction, users...
Several recent works on self-supervised learning are trained by mapping
...
Recent self-supervised learning methods are able to learn high-quality i...
Active learning is a paradigm aimed at reducing the annotation effort by...
Session-based recommenders, used for making predictions out of users'
un...
Research on continual learning has led to a variety of approaches to
mit...
Class-incremental learning of deep networks sequentially increases the n...
Recurrent neural networks (RNN) are popular for many computer vision tas...