Reconstruct & Crush Network

Abstract : This article introduces an energy-based model that is adversarial regarding data: it minimizes the energy for a given data distribution (the positive samples) while maximizing the energy for another given data distribution (the negative or unlabeled samples). The model is especially instantiated with autoencoders where the energy, represented by the reconstruction error, provides a general distance measure for unknown data. The resulting neural network thus learns to reconstruct data from the first distribution while crushing data from the second distribution. This solution can handle different problems such as Positive and Unlabeled (PU) learning or covariate shift, especially with imbalanced data. Using autoencoders allows handling a large variety of data, such as images, text or even dialogues. Our experiments show the flexibility of the proposed approach in dealing with different types of data in different settings: images with CIFAR-10 and CIFAR-100 (not-in-training setting), text with Amazon reviews (PU learning) and dialogues with Facebook bAbI (next response classification and dialogue completion).
Document type :
Conference papers
Complete list of metadatas

Cited literature [27 references]  Display  Hide  Download
Contributor : Matthieu Geist <>
Submitted on : Monday, November 6, 2017 - 5:17:17 PM
Last modification on : Tuesday, April 24, 2018 - 1:30:47 PM


Files produced by the author(s)


  • HAL Id : hal-01629742, version 1


Erinc Merdivan, Mohammad Loghmani, Matthieu Geist. Reconstruct & Crush Network. Advances in Neural Information Processing Systems, 2017, Long Beach, United States. ⟨hal-01629742⟩



Record views


Files downloads