PhD candidate

University of Amsterdam

I am a fourth-year PhD student in Machine Learning at the University of Amsterdam, advised by Prof. Max Welling. My main area of interest is learning with structured data and structured representations/computations. This includes topics in reasoning, (multi-agent) reinforcement learning, and structured deep generative models.

My formal background is in Physics (M.Sc. hons. 2016, B.Sc. 2014 at FAU). During my studies, I have had exposure to a number of fields and—after a short interlude in Neuroscience-related research at the Max Planck Institute for Brain Research—eventually found my way into Machine Learning.

- 05/2019: I gave a tutorial on Unsupervised Learning with Graph Neural Networks at the UCLA IPAM Workshop on Deep Geometric Learning of Big Data (slides, video).
- 04/2019: Our work on Compositional Imitation Learning is accepted at ICML 2019 as a long oral.
- 03/2019: I am co-organizing two workshops: Representation Learning on Graphs and Manifolds (ICLR 2019) and Learning and Reasoning with Graph-Structured Data (ICML 2019).
- 12/2018: My DeepMind internship project Compositional Imitation Learning: Explaining and executing one task at a time is accepted as a contributed talk at the Learning by Instruction Workshop at NeurIPS 2018.
- 06/2018: Our work on Relational GCNs has won the best student research paper award at ESWC 2018.
- 05/2018: Our work on learning latent interaction graphs: Neural Relational Inference for Interacting Systems is accepted as a conference paper at ICML 2018.

Unsupervised, differentiable sequence segmentation for option discovery.

T. Kipf, Y. Li, H. Dai, V. Zambaldi, A. Sanchez-Gonzales, E. Grefenstette, P. Kohli, P. Battaglia, Compositional Imitation Learning: Explaining and executing one task at a time, (ICML 2019), Long Oral [Link, PDF (arXiv)].

Learning the latent interaction graph of a dynamical system

T. Kipf*, E. Fetaya*, K. Wang, M. Welling, R. Zemel, Neural Relational Inference for Interacting Systems, (ICML 2018) [Link, PDF (arXiv), code], *equal contribution.

Learning to generate molecular graphs using a combined GAN/RL-based objective

N. De Cao, T. Kipf, MolGAN: An implicit generative model for small molecular graphs, ICML Deep Generative Models Workshop (2018) [Link, PDF (arXiv), code].

Learning hyperspherical latent spaces

T. R. Davidson*, L. Falorsi*, N. De Cao*, T. Kipf, J. M. Tomczak, Hyperspherical Variational Auto-Encoders, (UAI 2018), Plenary Talk [Link, PDF (arXiv), code, blog], *equal contribution.

Graph refinement with graph neural nets

R. Selvan, T. Kipf, M. Welling, J. H. Pedersen, J. Petersen, M. de Bruijne, Extraction of Airways using Graph Neural Networks, (MIDL 2018 - short paper) [Link, PDF (arXiv)].

Link prediction and entity classification on knowledge graphs

M. Schlichtkrull*, T. N. Kipf*, P. Bloem, R. vd Berg, I. Titov, M. Welling, Modeling Relational Data with Graph Convolutional Networks, (ESWC 2018), Best Student Research Paper [Link, PDF (arXiv), code], *equal contribution.

Collaborative filtering with side information in bipartite graphs

R. vd Berg, T. N. Kipf, M. Welling, Graph Convolutional Matrix Completion, KDD Deep Learning Day (2018), Spotlight Talk [Link, PDF (arXiv), code]

Neural networks for node classification on graphs

T. N. Kipf, M. Welling, Semi-Supervised Classification with Graph Convolutional Networks (ICLR 2017) [Link, PDF (arXiv), code, blog]

A latent variable model for graph-structured data

T. N. Kipf, M. Welling, Variational Graph Auto-Encoders, (NeurIPS Bayesian Deep Learning Workshop 2016) [Link, PDF (arXiv), code]

M.Sc. thesis (2016), Department of Connectomics, MPI for Brain Research

Thesis copy available here: [PDF (9 MB)]

For a full list, have a look at my Google Scholar page.