We have an opening for a 2-year postdoc – more details are available here – on a project titled Gradient-based Learning of Complex Latent Structures, with me as the Principal Investigator (PI), and Antonio Vergari (IANC) and Edoardo Ponti (ILCC) as co-PIs. The position is entirely funded by the Edinburgh Laboratory for Integrated Artificial Intelligence (ELIAI) – if you want to know more, feel free to reach out!
You can apply at this link.
Imposing structural constraints on the latent representations learned by deep neural models has several applications, which can improve their explainability, their robustness, and their ability to generalise to out-of-domain distributions. For example, we can learn more explainable models by making them selectively decide which parts of the input to consider; and we can improve their generalisation properties by learning representations suitable for reasoning tasks, such as deductive reasoning and planning, and comply with any desired constraints. For instance, the intermediate structure can represent a relational graph between objects in the world; the relationships between multiple sub-questions in a complex question; or computation graphs which can be executed to produce a prediction.
In this project, we aim to investigate how we can derive better methods for back-propagating through mixed continuous-discrete complex latent structures, and how we can leverage them for learning more explainable, data-efficient, and robust deep neural models. The reason why discrete latent representations are not widely adopted by deep neural models is that they tend to not interact well with gradient-based optimisation methods, but this started to change recently (e.g., see Niepert et al., 2021; Minervini et al. 2022), enabling a wide range of applications and use cases.
- Niepert, Minervini, and Franceschi - Implicit MLE: Backpropagating Through Discrete Exponential Family Distributions. NeurIPS 2021
- Minervini, Franceschi, and Niepert - Adaptive Perturbation-Based Gradient Estimation for Discrete Latent Variable Models. AAAI 2023
- Ahmed, Teso, Chang, Van den Broeck, Vergari - Semantic Probabilistic Layers for Neuro-Symbolic Learning. NeurIPS 2022
The post holder will work on projects involving the design and application of deep learning models with discrete latent structures for improving their explainability, generalisation, and robustness properties. They will be part of the new Edinburgh Laboratory for Integrated Artificial Intelligence and the Edinburgh NLP Group, a world-leading research group in Natural Language Processing.
The School of Informatics is one of the largest research centres in Computer Science in Europe, and it has been ranked #1 in the UK in terms of research power by a large margin. The Edinburgh NLP Group is consistently ranked among the world’s leading research groups in Natural Language Processing. We are offering an exciting opportunity to work in an interdisciplinary, collaborative, friendly, and supportive environment, integrating different sub-fields of Computer Science and Artificial Intelligence.