No photo of Vikas Verma
  • Aalto SCI Computer Science Konemiehentie 2

20172020

Research output per year

If you made any changes in Pure these will be visible here soon.

Research Output

  • 6 Conference contribution
  • 2 Paper
  • 2 Working paper
2020

GraphMix: Regularized Training of Graph Neural Networks for Semi-Supervised Learning

Verma, V., Qu, M., Lamb, A., Bengio, Y., Kannala, J. & Jian, T., 2020, (In preparation).

Research output: Working paperScientific

InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization

Sun, F-Y., Hoffman, J., Verma, V. & Tang, J., 2020, (Accepted/In press) International Conference on Learning Representations.

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

SketchTransfer: A New Dataset for Exploring Detail-Invariance and the Abstractions Learned by Deep Networks

Lamb, A., Ozair, S., Verma, V. & Ha, D., 2020, (Accepted/In press) 2020 Winter Conference on Applications of Computer Vision (WACV ’20).

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Towards understanding generalization in gradient-based meta-learning

Guiroy, S., Verma, V. & Pal, C., 2020, (Submitted).

Research output: Working paperScientific

2019

Adversarial mixup resynthesizers

Beckham, C., Honari, S., Verma, V., Lamb, A., Ghadiri, F., Hjelm, R. D. & Pal, C., 1 Jan 2019.

Research output: Contribution to conferencePaperScientificpeer-review

Interpolated Adversarial Training: Achieving Robust Neural Networks Without Sacrificing Too Much Accuracy

Verma, V., Lamb, A., Kannala, J. & Bengio, Y., 2019, AISec'19: Proceedings of the 12th ACM Workshop on Artificial Intelligence and Security. ACM, p. 95-103

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Open Access
File
39 Downloads (Pure)

Interpolation consistency training for semi-supervised learning

Verma, V., Lamb, A., Kannala, J., Bengio, Y. & Lopez-Paz, D., 2019, Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence (IJCAI-19). p. 3635-3641

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Open Access

Manifold Mixup: Better Representations by Interpolating Hidden States

Verma, V., Lamb, A., Beckham, C., Najafi, A., Mitliagkas, I., Lopez-Paz, D. & Bengio, Y., 2019, Proceedings of the 36th International Conference on Machine Learning. (Proceedings of Machine Learning Research; vol. 97).

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Open Access
File
11 Downloads (Pure)

On Adversarial Mixup Resynthesis

Beckham, C., Honari, S., Verma, V., Lamb, A., Ghadiri, F., Hjelm, R. D., Bengio, Y. & Pal, C., 2019, 33rd Conference on Neural Information Processing Systems: NeurIPS 2019 . Neural Information Processing Systems Foundation, (Advances in Neural Information Processing Systems).

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Open Access
2018

Residual connections encourage iterative inference

Ebski, S. J., Arpit, D., Ballas, N., Verma, V., Che, T. & Bengio, Y., 1 Jan 2018, p. 1-14.

Research output: Contribution to conferencePaperScientificpeer-review