Federated Learning with Only Positive Labels
12. července 2020
Řečníci
Ankit Singh Rawat
Řečník · 0 sledujících
Sanjiv Kumar
Řečník · 2 sledující
Aditya Krishna Menon
Řečník · 0 sledujících
Felix X. Yu
Řečník · 0 sledujících
O prezentaci
We consider learning a multi-class classification model in the federated setting, where each user has access to the positive data associated with only a single class. As a result, during each federated learning round, the users need to locally update the classifier without having access to the features and the model parameters for the negative labels. Since the loss function at a user is independent of the negative labels, naively employing conventional decentralized learning such as the distributed SGD or Federated Averaging may lead to trivial or extremely poor classifiers. In particular, for the embedding based classifiers, all the class embeddings might collapse to a single point. To address this problem, we propose a generic framework for training with only positive labels, namely Federated Averaging with Spreadout (FedAwS), where the server imposes a geometric regularizer after each round to encourage classes spread out in the embedding space. We show, both theoretically and empirically, that FedAwS can almost match the performance of conventional learning where users have access to negative labels. We further extend the proposed method to the settings with large output spaces, such as the extreme multi-class classification.We consider learning a multi-class classification model in the federated setting, where each user has access to the positive data associated with only a single class. As a result, during each federated learning round, the users need to locally update the classifier without having access to the features and the model parameters for the negative labels. Since the loss function at a user is independent of the negative labels, naively employing conventional decentralized learning such as the distrib…
Kategorie
Umělá inteligence a data science
Kategorie · 10,8k prezentací
O organizátorovi (ICML 2020)
The International Conference on Machine Learning (ICML) is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence known as machine learning. ICML is globally renowned for presenting and publishing cutting-edge research on all aspects of machine learning used in closely related areas like artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition, and robotics. ICML is one of the fastest growing artificial intelligence conferences in the world. Participants at ICML span a wide range of backgrounds, from academic and industrial researchers, to entrepreneurs and engineers, to graduate students and postdocs.
Baví vás formát? Nechte SlidesLive zachytit svou akci!
Profesionální natáčení a streamování po celém světě.
Sdílení
Doporučená videa
Prezentace na podobné téma, kategorii nebo přednášejícího
DeBayes: a Bayesian method for debiasing network embeddings
Zhlédnout později
Maarten Buyl, …
Calibrated Top-1 Uncertainty estimates for classification by score based models
Zhlédnout později
Invited Talk 4 Q&A
Zhlédnout později
Einsum Networks: Fast and Scalable Learning of Tractable Probabilistic Circuits
Zhlédnout později
Retrospective Publish ´Til You Perish
Zhlédnout později
Uniform Convergence of Rank-Weighted Learning
Zhlédnout později
Liu Leqi, …