Besides research and communication, I am an enthusiastic advisor and educator (primarily for machine learning, but I’m occasionally trying to expand into other areas of computer science and mathematics).

The best way to understand something is to explain it to somebody else.

Guided by this quote, I have readily taken up teaching, lecturing and advising throughout my PhD, and am still keen to advise interesting projects, whenever appropriate. Please consult my contact page if you are interested!

Lecturing

Alongside Pietro Liò, I am co-teaching the Geometric Deep Learning (L65) Master’s course at Cambridge. This is a geometry-oriented variation of the Representation Learning on Graphs and Networks (L45) course which we have delivered in 2022 and 2023, which is itself an extended version of the Graph Neural Networks module for the Advanced topics in machine learning or natural language processing (R250) course, which we have delivered in 2021.

Alongside Michael Bronstein, Joan Bruna and Taco Cohen, I have co-taught the Geometric Deep Learning (GDL100) Master’s course for the African Master’s in Machine Intelligence, in 2021 and 2022. This course follows our GDL proto-book and we have made all artifacts and resources publicly available! I have also given an adapted version of this course for the 47th Heidelberg Physics Graduate Days.

Alongside Andrew Dudzik, Bruno Gavranović, João Guilherme Araújo and Pim de Haan, I have co-taught the Categories for AI (Cats4AI) online course, introducing category-theoretic concepts relevant to deep learning research to a diverse group of several thousand attendees. We have made all artifacts and resources publicly available!

I have, on several occasions, also held formal (guest) lectures to undergraduate and postgraduate students:

• Categorical Deep Learning: An Algebraic Theory of Architectures. Applied Category Theory for Engineering Design (1.S980), Massachusetts Institute of Technology, 25 November 2024.
• A peek into graph rewiring. Statistical Machine Learning (STAT0042), University College London, 4 December 2023.
• Representation Learning on Graphs and Networks. Mathematical Foundations of Machine Learning (MATH70134), Imperial College London, 14 March 2023.
• Representation Learning on Graphs and Networks. Deep Neural Networks (DNN), University of Cambridge, 9 March 2023.
• Neural Algorithmic Reasoning: How to Train your Algorithm. Geometric Deep Learning (GeoDL), University of Oxford, 7 March 2023.
• Geometric Deep Learning: GNNs Beyond Permutation Equivariance. Machine Learning on Graphs (CS224W), Stanford University, 30 November 2021.
• Everything is Connected: Graph Neural Networks from the Ground Up. Deep Learning Course (UVADLC), Universiteit van Amsterdam. 26 November 2021.
• Neural Algorithmic Reasoning. Network Data Science 2 (PHYS 7332), Northeastern University, 2 April 2021.
• Be nice to your neurons: Initialisation, Normalisation, Optimisation and Regularisation. Introduction to Deep Learning (COMPGI23), University College London, 14 November 2017.
• Unsupervised methods: Diving deep into autoencoders. Introduction to Deep Learning (COMPGI23), University College London, 10 October 2017.
• A trip down long short-term memory lane. Research Students Lecture Series, University of Cambridge, 21 February 2017.
• Exactly solving TSP using the Simplex algorithm (with Thomas Sauerwald). Advanced Algorithms, University of Cambridge, 13 May 2016.

Furthermore, I have been in charge of designing the practical session on neural networks for the Cambridge MPhil course on Machine Learning and Algorithms for Data Mining (L42).

Supervising

Throughout my time at Cambridge, I have been extremely fortunate to (co-)supervise the project work of several students, whose dissertation titles are outlined below. Most of these disseratations have been turned into research publications, and many of the students are now working in prominent AI labs (either as doctoral students or research engineers).

Undergraduate projects

• Ioana Bica (2017) Comparative Analysis of Neural Network Architectures for Epigenetics Inference.
• Momchil Peychev (2017) Experimental Study on the Properties of Disentangled Autoencoders.
• Tudor Petru Țiplea (2017) An end-to-end control policy system for the GameBoy platform. (Highly commended dissertation)
• Andreea-Ioana Deac (2018) Neural architectures for end-to-end paratope prediction.
• Aliyah Bond (2019) Intelligent navigation of text adventure games.
• Carlos Purves (2019) The PlayStation reinforcement learning environment.
• Euan Ong (2023) Probing the foundations of neural algorithmic reasoning. (Best Dissertation Award)
• Kaijia Xu (2024) Asynchronous Graph Neural Networks.

Master’s projects

• Benjamin Day (2016) Combining Machine Learning & Multilayer Network Theory.
• Edgaras Liberis (2017) Antibody Binding Residue Prediction.
• Laurynas Karazija (2017) Automatic inference of cross-modal connection topologies for X-CNNs. (Dr John Maheswaran Prize for a Highly Commended Project Report)
• Cătălina Cangea (2017) 1D-2D Cross-modality for deep audiovisual classification.
• Miloš Stanojević (2018) Neural network hyperparameter optimisation on small validation sets.
• Nathaniel McAleese-Park (2018) Cross-modal learning for the joint understanding of 2D and 3D data.
• Aaron Solomon (2019) Dynamic temporal analysis for graph structured data.
• Felix Opolka (2019) Representation learning for spatio-temporal graphs.
• Rishabh Jain (2023) Differentiable Priority Queues for Graph Neural Networks.
• Vladimir Viktor Mirjanić (2023) Latent Space Representations of Neural Algorithmic Reasoners. (Examiners’ Highly Commended Prize)
• Riccardo Maria Ali (2024) Towards Category-Theoretic Message Passing.

Reviewer duties

I serve as reviewer, area chair (marked with *) and senior area chair/action editor (marked with **) for several major machine learning conferences, journals and workshops, always striving to provide the most actionable feedback possible. My efforts have been recognised with best reviewer awards at all of the “big three” machine learning conferences: NeurIPS 2019, ICML 2020 and ICLR 2021. I have also been honoured to receive the Top Area Chair award at LoG on three occasions (2022, 2023, 2024).

Conferences

• Neural Information Processing Systems (NeurIPS) 2019, 2020, 2021, 2022, 2023*, 2024**
• International Conference on Machine Learning (ICML) 2020
• International Conference on Learning Representations (ICLR) 2020, 2021, 2022, 2023*, 2024*, 2025*
• Learning on Graphs (LoG) 2022*, 2023*, 2024*
• The AAAI Conference on Artificial Intelligence (AAAI) 2022
• International Joint Conference on Artificial Intelligence (IJCAI) 2021
• International Joint Conference on Neural Networks (IJCNN) 2019
• European Symposium on Artificial Neural Networks (ESANN) 2018

Journals

• Nature Communications
• Nature Machine Intelligence
• Communications Medicine
• Proceedings of the National Academy of Science (PNAS)
• Journal of Machine Learning Research (JMLR)
• Transactions on Machine Learning Research (TMLR)**
• Machine Learning: Science and Technology
• IEEE Computer

Workshops

• Scientific Methods for Understanding Deep Learning (SciForDL) Workshop at NeurIPS 2024
• System 2 Reasoning at Scale (S2R) Workshop at NeurIPS 2024
• Symmetry and Geometry in Neural Representations (NeurReps) Workshop at NeurIPS 2024
• New Frontiers in Graph Learning (GLFrontiers) Workshop at NeurIPS 2022*, 2023*
• GroundedML: Anchoring Machine Learning in Classical Algorithmic Theory Workshop at ICLR 2022
• Wordplay: When Language Meets Games Workshop at NeurIPS 2020
• Deep Learning on Graphs: Methods and Applications (DLG) Workshop at KDD 2020
• Bridge Between Perception and Reasoning: Graph Neural Networks & Beyond Workshop at ICML 2020
• Learning and Reasoning with Graph-Structured Representations Workshop at ICML 2019
• Representation Learning on Graphs and Manifolds (RLGM) Workshop at ICLR 2019

Public policy 🇷🇸🇲🇪🇬🇧

I serve on the Scientific Advisory Board of the Institute for AI Research and Development of Serbia.

I have participated in a working group for developing the curriculum for the fourth year of Serbian grammar schools for gifted students in Mathematics and IT. For the first time, we have introduced a regular taught module on Contemporary Artificial Intelligence, with its materials available for all.

Alongside my colleagues from Google DeepMind and researchers from the Raspberry Pi Foundation, I have contributed to and steered the development of Experience AI, a new educational programme that offers cutting-edge KS3 (ages 11–14) resources on artificial intelligence and machine learning for teachers and their students—supporting the next generation of AI leaders in the UK. Since its initial launch, Google announced significant funding for the program, helping it reach millions of young people worldwide.

I serve on the Advisory Board of the Montenegrin AI Association, a non-governmental organisation founded with an ambition to bring together the Montenegrin AI community.

I’ve participated in developing Serbia’s AI Strategy for 2020–2025, as one of the representatives of Serbian machine learning researchers working abroad. The Government of Serbia had officially adopted it on 26 December 2019.

The Strategy defines objectives and measures for the development of AI, whose implementation should result in economic growth, improvement of public services, advancement of scientific staff, and development of skills for the jobs of the future. Also, the implementation of the Strategy measures should ensure that AI in the Republic of Serbia is developed and implemented in a safe manner and in accordance with internationally recognised ethical principles, in order to exploit the potential of this technology to improve the quality of life of each individual and the society as a whole, as well as to achieve Sustainable Development Goals.

Between 2020 and 2022, I served on the Advisory Board of the Serbian AI Society, an organisation aiming to develop and maintain a plan for the improvement of the Serbian AI ecosystem in the coming years.