Research License — ACOT

Adversarially-Contrastive Optimal Transport for studying the problem of learning compact representations for sequential data that captures its implicit spatio-temporal cues.

In this software release, we provide a PyTorch implementation of the adversarially-contrastive optimal transport (ACOT) algorithm. Through ACOT, we study the problem of learning compact representations for sequential data that captures its implicit spatio-temporal cues. To separate such informative cues from the data, we propose a novel contrastive learning objective via optimal transport. Specifically, our formulation seeks a low-dimensional subspace representation of the data that jointly (i) maximizes the distance of the data (embedded in this subspace) from an adversarial data distribution under a Wasserstein distance, (ii) captures the temporal order, and (iii) minimizes the data distortion. To generate the adversarial distribution, we propose to use a Generative Adversarial Network (GAN) with novel regularizers. Our full objective can be cast as a subspace learning problem on the Grassmann manifold, and can be solved efficiently via Riemannian optimization. The associated software implements all components of our algorithm.

  •  Cherian, A., Aeron, S., "Representation Learning via Adversarially-Contrastive Optimal Transport", International Conference on Machine Learning (ICML), H. Daumé and A. Singh, Eds., July 2020, pp. 10675-10685.
    BibTeX TR2020-093 PDF Software
    • @inproceedings{Cherian2020jul,
    • author = {Cherian, Anoop and Aeron, Shuchin},
    • title = {Representation Learning via Adversarially-Contrastive Optimal Transport},
    • booktitle = {International Conference on Machine Learning (ICML)},
    • year = 2020,
    • editor = {H. Daumé and A. Singh},
    • pages = {10675--10685},
    • month = jul,
    • url = {https://www.merl.com/publications/TR2020-093}
    • }

To download the software, please enter some information about yourself, then review and agree to MERL's research-only licensing terms. (Information is collected for auditing purposes.)

    Software:
    Name:
    Affiliation:
    Street Address:
    City, State, Country, Postal Code:
    E-Mail:
    Confirm E-Mail:
    IP Address: