Personal profile

Research Interests

My research interests lie on the intersection of Machine Learning and the expectations we place on them. I am interested on how to design models that are robust, trustworthy, and that behave in a coherent way relatively to what we expect. In particular, I look into ways that we can incorporate prior knowledge (e.g. the trade-off we want to achieve between different tasks, the causal relationship between variables) such that the model respects this knowledge and thus do not violate our domain constraints. Moreover, I am interested in a number of related topics such as:
- Reasoning with ML models,
- Neuro-symbolic AI,
- Generative probabilistic models,
- Model identifiability.

Qualifications

2024, PhD in Machine Learning, Saarland University

2018, MSc, Advanced Computer Science, University of Murcia

2018, BSc, Computer Science Engineering, University of Murcia

2017, BSc, Mathematics, University of Murcia

Fingerprint

Dive into the research topics where Adrian Javaloy is active. These topic labels come from the works of this person. Together they form a unique fingerprint.
  • 1 Similar Profiles

Collaborations and top research areas from the last five years

Recent external collaboration on country/territory level. Dive into details by clicking on the dots or
  • Causal normalizing flows: From theory to practice

    Javaloy, A., Sánchez-Martín, P. & Valera, I., 16 Dec 2023, Advances in Neural Information Processing Systems 36 (NeurIPS 2023). Oh, A., Naumann, T., Globerson, A., Saenko, K., Hardt, M. & Levine, S. (eds.). Neural Information Processing Systems Foundation (NeurIPS), p. 1-32 32 p. (Advances in Neural Information Processing Systems).

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Open Access
  • Learnable graph convolutional attention networks

    Javaloy, A., Sánchez-Martín, P., Levi, A. & Valera, I., 5 May 2023, p. 1-35. 35 p.

    Research output: Contribution to conferencePaperpeer-review

    Open Access
  • Mitigating modality collapse in multimodal VAEs via impartial optimization

    Javaloy, A., Meghdadi, M. & Valera, I., 23 Jul 2022, Proceedings of the 39th International Conference on Machine Learning. Chaudhuri, K., Jegelka, S., Song, L., Szepesvari, C., Niu, G. & Sabato, S. (eds.). PMLR, Vol. 162. p. 9938-9964 27 p.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Open Access
    File
  • RotoGrad: Gradient homogenization in multitask learning

    Javaloy, A. & Valera, I., 28 Jan 2022, p. 1-24. 24 p.

    Research output: Contribution to conferencePaperpeer-review

    Open Access
    File
  • Relative gradient optimization of the Jacobian term in unsupervised deep learning

    Gresele, L., Fissore, G., Javaloy, A., Schölkopf, B. & Hyvärinen, A., 12 Dec 2020, Advances in Neural Information Processing Systems 33 (NeurIPS 2020). Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M. F. & Lin, H. (eds.). Neural Information Processing Systems Foundation (NeurIPS), Vol. 33. p. 1-12 12 p. (Advances in Neural Information Processing Systems).

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Open Access