Federated Learning with Only Positive Labels

By Felix X. Yu, Ankit Singh Rawat, Aditya Krishna Menon, Sanjiv Kumar. 2020

125 citations recorded by the source corpus.

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 classes. Thus, 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 to be spreadout 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.

Subfields: Artificial Intelligence, Computer Science Applications

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Qiang Yang
2. Murali Annavaram
3. Chaoyang He
4. Yang Liu
5. Bingsheng He
6. Qinbin Li
7. S. Avestimehr
8. Jiankun Hu

In Computer Science Applications

1. Bingsheng He
2. Peilin Zhao
3. Murali Annavaram
4. Ramesh Raskar
5. Qiang Yang
6. Jiankun Hu
7. Yanming Zhu
8. Praneeth Vepakomma

Citations in the corpus

• FedML: A Research Library and Benchmark for Federated Machine Learning (2020, methodology): “ICML 2020 Federated Learning with Only Positive Labels [149] CIFAR-10 1 class / client ResNet-8/32 CIFAR-100 1 class / client ResNet-56 AmazonCAT 1 class / client Fully Connected Nets WikiLSHTC 1 class / client Amazon670K 1 class / client ICML 2020 SCAFFOLD: Stochastic Controlled Averaging for Feder”
• Federated Learning on Non-IID Data Silos: An Experimental Study (2021, background): “[13] considers a highly extreme case, where each party only has data samples with a single label.”
• A Comprehensive Survey of Privacy-preserving Federated Learning (2021, background): “The focuses of FL research can be roughly divided into three aspects: (1) improving the efficiency and effectiveness of FL [24, 68, 87, 100, 120, 211, 213], (2) improving the security of FL to attacks that aim to undermine the integrity of FL models and degrade the model performance [9, 13, 185, 198”