Intelligent Systems
Note: This research group has relocated. Discover the updated page here


2022


no image
Don’t Throw it Away! The Utility of Unlabeled Data in Fair Decision Making

Rateike, M., Majumdar, A., Mineeva, O., Gummadi, K. P., Valera, I.

In FAccT ’22: 2022 ACM Conference on Fairness, Accountability, and Transparency, pages: 1421-1433, ACM, New York, NY, 5th ACM Conference on Fairness, Accountability, and Transparency (FAccT 2022), June 2022 (inproceedings)

DOI [BibTex]

2022

DOI [BibTex]


On the Fairness of Causal Algorithmic Recourse
On the Fairness of Causal Algorithmic Recourse

von Kügelgen, J., Karimi, A., Bhatt, U., Valera, I., Weller, A., Schölkopf, B.

Proceedings of the 36th AAAI Conference on Artificial Intelligence, 9, pages: 9584-9594, AAAI Press, Palo Alto, CA, Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI 2022), February 2022, *also at ICML 2021 Workshop Algorithmic Recourse and NeurIPS 2020 Workshop Algorithmic Fairness through the Lens of Causality and Interpretability (AFCI) (conference)

arXiv link (url) DOI Project Page [BibTex]

arXiv link (url) DOI Project Page [BibTex]


no image
VACA: Designing Variational Graph Autoencoders for Causal Queries

Sanchez-Martin, P., Rateike, M., Valera, I.

In Proceedings of the 36th AAAI Conference on Artificial Intelligence, 7, pages: 8159-8168, AAAI Press, Palo Alto, CA, Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI 2022), February 2022 (inproceedings)

Abstract
In this paper, we introduce VACA, a novel class of vari- ational graph autoencoders for causal inference in the ab- sence of hidden confounders, when only observational data and the causal graph are available. Without making any para- metric assumptions, VACA mimics the necessary properties of a Structural Causal Model (SCM) to provide a flexible and practical framework for approximating interventions (do- operator) and abduction-action-prediction steps. As a result, and as shown by our empirical results, VACA accurately ap- proximates the interventional and counterfactual distributions on diverse SCMs. Finally, we apply VACA to evaluate coun- terfactual fairness in fair classification problems, as well as to learn fair classifiers without compromising performance.

DOI [BibTex]

DOI [BibTex]

2021


no image
Scaling Guarantees for Nearest Counterfactual Explanations

Mohammadi, K., Karimi, A., Barthe, G., Valera, I.

AIES ’21: Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society, pages: 177-187, (Editors: Marion Fourcade, Benjamin Kuipers, Seth Lazar and Deirdre K. Mulligan), ACM, New York, NY, Fourth AAAI/ACM Conference on AI, Ethics, and Society (AIES 2021), May 2021 (conference)

arXiv DOI Project Page [BibTex]

2021

arXiv DOI Project Page [BibTex]


no image
Algorithmic Recourse: from Counterfactual Explanations to Interventions

Karimi, A., Schölkopf, B., Valera, I.

FAccT ’21: Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency, pages: 353-362, (Editors: Madeleine Clare Elish and William Isaac and Richard S. Zemel), ACM, New York, NY, ACM Conference on Fairness, Accountability, and Transparency (FAccT 2021), March 2021 (conference)

link (url) DOI Project Page [BibTex]

link (url) DOI Project Page [BibTex]

2020


Algorithmic recourse under imperfect causal knowledge: a probabilistic approach
Algorithmic recourse under imperfect causal knowledge: a probabilistic approach

Karimi*, A., von Kügelgen*, J., Schölkopf, B., Valera, I.

Advances in Neural Information Processing Systems 33 (NeurIPS 2020), pages: 265-277, (Editors: H. Larochelle and M. Ranzato and R. Hadsell and M. F. Balcan and H. Lin), Curran Associates, Inc., 34th Annual Conference on Neural Information Processing Systems, December 2020, *equal contribution (conference)

arXiv link (url) Project Page [BibTex]

2020

arXiv link (url) Project Page [BibTex]


no image
Relative gradient optimization of the Jacobian term in unsupervised deep learning

Gresele, L., Fissore, G., Javaloy, A., Schölkopf, B., Hyvarinen, A.

Advances in Neural Information Processing Systems 33 (NeurIPS 2020), pages: 16567-16578, (Editors: H. Larochelle and M. Ranzato and R. Hadsell and M. F. Balcan and H. Lin), Curran Associates, Inc., 34th Annual Conference on Neural Information Processing Systems, December 2020 (conference)

link (url) Project Page [BibTex]

link (url) Project Page [BibTex]


no image
Model-Agnostic Counterfactual Explanations for Consequential Decisions

Karimi, A., Barthe, G., Balle, B., Valera, I.

Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics (AISTATS), 108, pages: 895-905, Proceedings of Machine Learning Research, (Editors: Silvia Chiappa and Roberto Calandra), PMLR, August 2020 (conference)

arXiv link (url) Project Page [BibTex]

arXiv link (url) Project Page [BibTex]


no image
Fair Decisions Despite Imperfect Predictions

Kilbertus, N., Gomez Rodriguez, M., Schölkopf, B., Muandet, K., Valera, I.

Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics (AISTATS), 108, pages: 277-287, Proceedings of Machine Learning Research, (Editors: Silvia Chiappa and Roberto Calandra), PMLR, August 2020 (conference)

link (url) Project Page [BibTex]

link (url) Project Page [BibTex]


From Variational to Deterministic Autoencoders
From Variational to Deterministic Autoencoders

Ghosh*, P., Sajjadi*, M. S. M., Vergari, A., Black, M. J., Schölkopf, B.

8th International Conference on Learning Representations (ICLR) , April 2020, *equal contribution (conference)

Abstract
Variational Autoencoders (VAEs) provide a theoretically-backed framework for deep generative models. However, they often produce “blurry” images, which is linked to their training objective. Sampling in the most popular implementation, the Gaussian VAE, can be interpreted as simply injecting noise to the input of a deterministic decoder. In practice, this simply enforces a smooth latent space structure. We challenge the adoption of the full VAE framework on this specific point in favor of a simpler, deterministic one. Specifically, we investigate how substituting stochasticity with other explicit and implicit regularization schemes can lead to a meaningful latent space without having to force it to conform to an arbitrarily chosen prior. To retrieve a generative mechanism for sampling new data points, we propose to employ an efficient ex-post density estimation step that can be readily adopted both for the proposed deterministic autoencoders as well as to improve sample quality of existing VAEs. We show in a rigorous empirical study that regularized deterministic autoencoding achieves state-of-the-art sample quality on the common MNIST, CIFAR-10 and CelebA datasets.

arXiv link (url) Project Page [BibTex]

arXiv link (url) Project Page [BibTex]

2019


no image
Random Sum-Product Networks: A Simple and Effective Approach to Probabilistic Deep Learning

Peharz, R., Vergari, A., Stelzner, K., Molina, A., Shao, X., Trapp, M., Kersting, K., Ghahramani, Z.

Proceedings of the 35th Conference on Uncertainty in Artificial Intelligence (UAI), 115, pages: 334-344, Proceedings of Machine Learning Research, (Editors: Adams, Ryan P. and Gogate, Vibhav), PMLR, July 2019 (conference)

link (url) [BibTex]

2019

link (url) [BibTex]


no image
Automatic Bayesian Density Analysis

Vergari, A., Molina, A., Peharz, R., Ghahramani, Z., Kersting, K., Valera, I.

Proceedings of the AAAI Conference on Artificial Intelligence (AAAI-19), 33:01, pages: 5207-5215, AAAI.org, AAAI-19, January 2019 (conference)

arXiv DOI [BibTex]

arXiv DOI [BibTex]

2018


no image
Enhancing the Accuracy and Fairness of Human Decision Making

Valera, I., Singla, A., Gomez Rodriguez, M.

Advances in Neural Information Processing Systems 31 (NeurIPS 2018), pages: 1774-1783, (Editors: S. Bengio and H. Wallach and H. Larochelle and K. Grauman and N. Cesa-Bianchi and R. Garnett), Curran Associates, Inc., 32nd Annual Conference on Neural Information Processing Systems, December 2018 (conference)

arXiv link (url) [BibTex]

2018

arXiv link (url) [BibTex]


no image
Boosting Black Box Variational Inference

Locatello*, F., Dresdner*, G., R., K., Valera, I., Rätsch, G.

Advances in Neural Information Processing Systems 31 (NeurIPS 2018), pages: 3405-3415, (Editors: S. Bengio and H. Wallach and H. Larochelle and K. Grauman and N. Cesa-Bianchi and R. Garnett), Curran Associates, Inc., 32nd Annual Conference on Neural Information Processing Systems, December 2018, *equal contribution (conference)

arXiv link (url) [BibTex]

arXiv link (url) [BibTex]


no image
Bayesian Nonparametric Hawkes Processes

Kapoor, J., Vergari, A., Gomez Rodriguez, M., Valera, I.

Bayesian Nonparametrics workshop at the 32nd Conference on Neural Information Processing Systems, December 2018 (conference)

PDF link (url) [BibTex]

PDF link (url) [BibTex]


no image
Probabilistic Deep Learning using Random Sum-Product Networks

Peharz, R., Vergari, A., Stelzner, K., Molina, A., Trapp, M., Kersting, K., Ghahramani, Z.

2018 (conference) Submitted

arXiv [BibTex]

arXiv [BibTex]

2017


no image
From Parity to Preference-based Notions of Fairness in Classification

Zafar, M. B., Valera, I., Gomez Rodriguez, M., Gummadi, K., Weller, A.

Advances in Neural Information Processing Systems 30 (NIPS 2017), pages: 229-239, (Editors: Guyon I. and Luxburg U.v. and Bengio S. and Wallach H. and Fergus R. and Vishwanathan S. and Garnett R.), Curran Associates, Inc., 31st Annual Conference on Neural Information Processing Systems, December 2017 (conference)

link (url) [BibTex]

2017

link (url) [BibTex]

2016


no image
On the Reliability of Information and Trustworthiness of Web Sources in Wikipedia

Tabibian, B., Farajtabar, M., Valera, I., Song, L., Schölkopf, B., Gomez Rodriguez, M.

Wikipedia workshop at the 10th International AAAI Conference on Web and Social Media (ICWSM), May 2016 (conference)

link (url) Project Page [BibTex]

2016

link (url) Project Page [BibTex]

2014


no image
Shaping Social Activity by Incentivizing Users

Farajtabar, M., Du, N., Gomez Rodriguez, M., Valera, I., Zha, H., Song, L.

In Advances in Neural Information Processing Systems 27, (Editors: Ghahramani, Z., Welling, M., Cortes, C., Lawrence, ND., and Weinberger, KQ.), Curran Associates, Inc., 28th Annual Conference on Neural Information Processing Systems (NIPS), 2014 (inproceedings)

Web link (url) [BibTex]

2014

Web link (url) [BibTex]