Theory and Evaluation Metrics for Learning Disentangled Representations

Preprint English OPEN
Do, Kien; Tran, Truyen;
  • Subject: Statistics - Machine Learning | Computer Science - Machine Learning

We make two theoretical contributions to disentanglement learning by (a) defining precise semantics of disentangled representations, and (b) establishing robust metrics for evaluation. First, we characterize the concept "disentangled representations" used in supervised ... View more
  • References (36)
    36 references, page 1 of 4

    [1] Error function., May 2019.

    [9] Xi Chen, Yan Duan, Rein Houthooft, John Schulman, Ilya Sutskever, and Pieter Abbeel. Infogan: Interpretable representation learning by information maximizing generative adversarial nets. In Advances in Neural Information Processing Systems, pages 2172-2180, 2016.

    [10] Taco Cohen and Max Welling. Learning the irreducible representations of commutative lie groups. In International Conference on Machine Learning, pages 1755-1763, 2014.

    [11] Guillaume Desjardins, Aaron Courville, and Yoshua Bengio. Disentangling factors of variation via generative entangling. arXiv preprint arXiv:1210.5474, 2012.

    [12] Cian Eastwood and Christopher KI Williams. A framework for the quantitative evaluation of disentangled representations. 2018.

    [13] Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. Generative adversarial nets. In Advances in Neural Information Processing Systems, pages 2672-2680, 2014.

    [14] Ananya Harsh Jha, Saket Anand, Maneesh Singh, and VSR Veeravasarapu. Disentangling factors of variation with cycle-consistent variational auto-encoders. In Proceedings of the European Conference on Computer Vision (ECCV), pages 805-820, 2018.

    [15] Irina Higgins, David Amos, David Pfau, Sebastien Racaniere, Loic Matthey, Danilo Rezende, and Alexander Lerchner. Towards a definition of disentangled representations. arXiv preprint arXiv:1812.02230, 2018.

    [16] Irina Higgins, Loic Matthey, Arka Pal, Christopher Burgess, Xavier Glorot, Matthew Botvinick, Shakir Mohamed, and Alexander Lerchner. Beta-vae: Learning basic visual concepts with a constrained variational framework. In International Conference on Learning Representations, 2017.

    [17] Irina Higgins, Nicolas Sonnerat, Loic Matthey, Arka Pal, Christopher P Burgess, Matko Bosnjak, Murray Shanahan, Matthew Botvinick, Demis Hassabis, and Alexander Lerchner. Scan: Learning hierarchical compositional visual concepts. arXiv preprint arXiv:1707.03389, 2017.

  • Related Research Results (2)
  • Related Organizations (3)
  • Metrics
Share - Bookmark