| CARVIEW |
Thomas Kipf
Senior Staff Research Scientist
Google DeepMind
I am a Senior Staff Research Scientist at Google DeepMind. I obtained my PhD at the University of Amsterdam working with Max Welling. For my PhD thesis on Deep Learning with Graph-Structured Representations I received the ELLIS PhD Award 2021. I am broadly interested in developing and studying machine learning models that can reason about the rich structure of both the physical and digital world and their combinatorial complexity.
News
Note: This hasn't been actively updated in a while. Follow me on Twitter for latest updates. See my talk on Learning Structured Models of the World for an overview of my recent work.
- 04/2022: I led the organization of the ICLR 2022 Workshop on the Elements of Reasoning: Objects, Structure, and Causality (OSC).
- 12/2021: I received the ELLIS PhD Award 2021.
- 11/2021: Our paper on Conditional Object-Centric Learning from Video will be presented at ICLR 2022.
- 10/2021: I was selected to be an ELLIS Scholar.
- 12/2020: I am an Area Chair at ICLR.
- 09/2020: Our paper on Object-centric Learning with Slot Attention is accepted for spotlight presentation at NeurIPS!
- 07/2020: I gave two invited workshop talks at ICML: Attentive Grouping and Relational Structure Discovery.
- 04/2020: I have defended my PhD thesis with highest distinction "cum laude". My thesis on "Deep Learning with Graph-Structured Representations" is available here.
- 01/2020: I have joined Google Brain as a Research Scientist in Amsterdam.
- 12/2019: I am co-organizing the ELLIS Workshop on Geometric and Relational Deep Learning.
- 12/2019: Our work on Contrastive Learning of Structured World Models is accepted at ICLR 2020 as an oral presentation.
- 08/2019: I am co-organizing the Graph Representation Learning workshop at NeurIPS 2019.
- 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).
- 06/2018: Our work on Relational GCNs has won the best student research paper award at ESWC 2018.
Selected Publications
Object-centric Learning with Slot Attention
Iterative, competitive attention for object discovery
F. Locatello*, D. Weissenborn, T. Unterthiner, A. Mahendran, G. Heigold, J. Uszkoreit, A. Dosovitskiy, T. Kipf*, Object-centric Learning with Slot Attention, (NeurIPS 2020), Spotlight [Link, PDF (arXiv)], *equal contribution.
Deep Learning with Graph-Structured Representations
PhD thesis (2020), University of Amsterdam
T. N. Kipf, Deep Learning with Graph-Structured Representations [Link]
Contrastive Learning of Structured World Models
Unsupervised discovery of objects, relations, and consequences of actions.
T. Kipf, E. van der Pol, M. Welling, Contrastive Learning of Structured World Models, (ICLR 2020), Oral [Link, PDF (arXiv)].
CompILE: Compositional Imitation Learning and Execution
Unsupervised, differentiable sequence segmentation for option discovery.
T. Kipf, Y. Li, H. Dai, V. Zambaldi, A. Sanchez-Gonzales, E. Grefenstette, P. Kohli, P. Battaglia, CompILE: Compositional Imitation Learning and Execution, (ICML 2019), Long Oral [Link, PDF (arXiv)].
Neural Relational Inference for Interacting Systems
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.
MolGAN: An implicit generative model for small molecular graphs
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].
Hyperspherical Variational Auto-Encoders
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.
Modeling Relational Data with Graph Convolutional Networks
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.
Semi-Supervised Classification with Graph Convolutional Networks
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]
Variational Graph Auto-Encoders
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]
For a full list, have a look at my Google Scholar page.