On May 25th 2021, I passed my PhD viva with no corrections! During my PhD at the Department of Computer Science and Technology, University of Cambridge, I have been supervised by Pietro Liò and a member of King’s College. My research focuses on learning multimodal and graph-structured representations of the world.
Until November 2020, I was a Research Scientist intern at DeepMind, hosted by Piotr Mirowski in the Robotics, Embodied Agents and Lifelong learning (REAL) team led by Raia Hadsell. I am co-organising the Visually Grounded Interaction and Language Workshop taking place at NAACL 2021.
My professional experience includes undergraduate Software Engineering internships at Google and Facebook. During the PhD, I was a Research Intern at Mila and an AI Resident at X. In 2020, I briefly worked for Relation Therapeutics as a (graph) ML consultant.
I have a great passion for teaching and am constantly involved in academic and departmental life - supervising undergraduate courses, final year projects and Master’s research projects (+200h and ~60 students), interviewing CS applicants, chairing women@CL and introducing professionals to Machine Learning concepts as a Cambridge Spark Teaching Fellow. I also helped prepare and deliver Master’s courses, both on the practical (L42 Neural Networks in 2018 and 2019) and theoretical side (R250 Graph Neural Network seminars in 2020 and 2021).
Outside work, I love rowing with the Women’s First Boat in King’s College, travelling, playing the piano/guitar/singing in a rock band and chasing my favourite bands on tour. 🎼 I’ve also revived an old habit of writing poetry and taken up cycling!
PhD in Machine Learning, 2021
University of Cambridge
MPhil in Advanced Computer Science, 2017
University of Cambridge
BA in Computer Science, 2016
University of Cambridge
Graph summarisation has received much attention lately, with various works tackling the challenge of defining pooling operators on data regions with arbitrary structures. These contrast the grid-like ones encountered in image inputs, where techniques such as max-pooling have been enough to show empirical success. In this work, we merge the Mapper algorithm with the expressive power of graph neural networks to produce topologically-grounded graph summaries. We demonstrate the suitability of Mapper as a topological framework for graph pooling by proving that Mapper is a generalisation of pooling methods based on soft cluster assignments. Building upon this, we show how easy it is to design novel pooling algorithms that obtain competitive results with other state-of-the-art methods.
Embodied Question Answering (EQA) is a recently proposed task, where an agent is placed in a rich 3D environment and must act based solely on its egocentric input to answer a given question. The desired outcome is that the agent learns to combine capabilities such as scene understanding, navigation and language understanding in order to perform complex reasoning in the visual world. However, initial advancements combining standard vision and language methods with imitation and reinforcement learning algorithms have shown EQA might be too complex and challenging for these techniques. In order to investigate the feasibility of EQA-type tasks, we build the VideoNavQA dataset that contains pairs of questions and videos generated in the House3D environment. The goal of this dataset is to assess question-answering performance from nearly-ideal navigation paths, while considering a much more complete variety of questions than current instantiations of the EQA task. We investigate several models, adapted from popular VQA methods, on our benchmark. This establishes an initial understanding of how well VQA-style methods can perform within the novel EQA paradigm.
Master’s research projects: Structure-aware Generation of Molecules in Protein Pockets (Pavol Drotar, 2020-21), Machine Unlearning (Mukul Rathi, 2020-21), Goal-Conditioned Reinforcement Learning in the Presence of an Adversary (Carlos Purves, 2019-20) (87⁄100), Representation Learning for Spatio-Temporal Graphs (Felix Opolka, 2018-19) (85⁄100) (presented at ICLR RLGM), Dynamic Temporal Analysis for Graph Structured Data (Aaron Solomon, 2018-19) (presented at ICLR RLGM)
Computer Science Tripos Part II projects: Benchmarking Graph Neural Networks using Wikipedia (Péter Mernyei, 2019-20, Novel Applications spotlight talk at ICML GRL+), Multimodal Relational Reasoning for Visual Question Answering (Aaron Tjandra, 2019-20), The PlayStation Reinforcement Learning Environment (Carlos Purves, 2018-19) (80⁄100) (presented at NeurIPS Deep RL), Deep Learning for Music Recommendation (Andrew Wells, 2017-18) (76⁄100).
Undergraduate courses for Murray Edwards, King’s, and Queens’ Colleges: AI, Databases, Discrete Mathematics, Foundations of Computer Science, Logic and Proof, Machine Learning and Real-world Data.