Christopher Morris

Contact

chris ät christophermorris.info
Université de Montréal Campus André-Aisenstadt Building 2920, Chemin de la Tour
@chrsmrrs
chrsmrrs

I am postdoc at Polytechnique Montréal in the group of Andrea Lodi. Previously, I was a PhD student at TU Dortmund University advised by Petra Mutzel and Kristian Kersting. My PhD research was generously supported by the German Research Foundation, through the Collaborative Research Center SFB 876 -- Providing Information by Resource-Constrained Data Analysis, Project A6.

I develop machine learning methods for graphs, network, and relational data.
My research combines techniques from machine learning, graph algorithms, and CS theory, and revolves around the following questions:

How do we effectively capture the structure of graphs and networks in a data-driven manner?
How can we scale up such methods for large-scale data?
How can such methods make combinatorial algorithms faster in a data-driven manner?

For more details, please refer to my CV.

Fun Fact: My Erdős number is at most 3 (via Petra Mutzel → Bojan Mohar → P. Erdős)

Conference Papers

Weisfeiler and Leman go sparse: Towards scalable higher-order graph embeddings (Preprint arXiv:1904:01543)
Christopher Morris, Gaurav Rattan, Petra Mutzel,
Neural Information Processing Systems (NeurIPS) 2020.

Deep Graph Matching Consensus (Preprint arXiv:2001:09621)
Matthias Fey, Jan E. Lenssen, Christopher Morris, Jonathan Masci, Nils M. Kriege,
International Conference on Learning Representations (ICLR) 2020.

Temporal Graph Kernels for Classifying Dissemination Processes (Preprint arXiv:1911.05496)
Lutz Oettershagen, Nils Kriege, Christopher Morris, Petra Mutzel,
SIAM International Conference on Data Mining (SDM) 2020.

Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks (Preprint arXiv:1810.02244)
Christopher Morris, Martin Ritzert, Matthias Fey, William L. Hamilton, Jan Eric Lenssen, Gaurav Rattan, Martin Grohe,
AAAI Conference on Artificial Intelligence (AAAI) 2019.
Source Code Slides

Hierarchical Graph Representation Learning with Differentiable Pooling (Preprint arXiv:1806.08804)
Rex Ying, Jiaxuan You, Christopher Morris, Xiang Ren, William L. Hamilton, Jure Leskovec,
Neural Information Processing Systems (NeurIPS) 2018, spotlight presentation, and KDD Deep Learning Day 2018.
Source Code

A Property Testing Framework for the Theoretical Expressivity of Graph Kernels
Nils M. Kriege, Christopher Morris, Anja Rey, Christian Sohler,
International Joint Conference on Artificial Intelligence (IJCAI) 2018.

Glocalized Weisfeiler-Lehman Graph Kernels: Global-Local Feature Maps of Graphs (Preprint arXiv:1703.02379)
Christopher Morris, Kristian Kersting, Petra Mutzel,
IEEE International Conference on Data Mining (IEEE ICDM) 2017, full paper.
Source Code Slides

Recent Advances in Kernel-Based Graph Classification
Nils M. Kriege, Christopher Morris,
European Conference on Machine Learning & Principles and Practice of Knowledge Discovery in Databases (ECML PKDD) 2017, nectar track.
Slides

Faster Kernels for Graphs with Continuous Attributes via Hashing (Preprint arXiv:1610.00064)
Christopher Morris, Nils M. Kriege, Kristian Kersting, Petra Mutzel,
IEEE International Conference on Data Mining (IEEE ICDM) 2016.
Source Code

Journal Papers

Output-sensitive Complexity of Multiobjective Combinatorial Optimization (Preprint arXiv:1610.07204)
Fritz Bökler, Matthias Ehrgott, Christopher Morris, Petra Mutzel,
Journal of Multicriteria Decision Analysis, 2016.

A Survey on Graph Kernels (Preprint arXiv:1903.11835)
Nils M. Kriege, Fredrik D. Johansson, Christopher Morris,
Applied Network Science, Machine learning with graphs, 2020.

A unifying view of explicit and implicit feature maps of graph kernels (Preprint arXiv:1703.00676)
Nils M. Kriege, Marion Neumann, Christopher Morris, Kristian Kersting, Petra Mutzel,
Data Mining and Knowledge Discovery, 2019.

Classifying Dissemination Processes in Temporal Graphs
Lutz Oettershagen, Nils M. Kriege, Christopher Morris, Petra Mutzel,
Big Data, 2020.

Workshop Papers

Weisfeiler and Leman go sparse: Towards scalable higher-order graph embeddings (Preprint arXiv:XXX.XXX)
Christopher Morris, Gaurav Rattan, Petra Mutzel,
Graph Representation Learning and Beyond (GRL+, ICML 2020).

TUDataset: A collection of benchmark datasets for learning with graphs (Preprint arXiv:XXX.XXX)
Christopher Morris, Nils M. Kriege, Franka Bause Kristian Kersting, Petra Mutzel, Marion Neumann,
Graph Representation Learning and Beyond (GRL+, ICML 2020).

Thesis

Learning with graphs: kernel and neural approaches
Christopher Morris.

News & Activities

12.12.2020–16.12.2020: NeurIPS 2020 (Paper)

08.11.2020–11.11.2020: INFORMS Annual Meeting (Invited session talk)

13.07.2020–18.07.2020: International Conference on Machine Learning (Two papers at the Graph Representation Learning and Beyond (GRL+) workshop)

27.01.2019–01.02.2019: AAAI Conference on Artificial Intelligence (Spotlight talk + poster)

02.12.2018–08.12.2018: Conference on Neural Information Processing Systems 2018 (Spotlight talk + poster)

15.01.2018–31.03.2018: Research stay at Stanford University with Jure Leskovec

18.11.2017–21.11.2017: IEEE International Conference on Data Mining 2017 (Talk)

18.09.2017–22.09.2017: ECML PKKD 2017 (Talk)

19.06.2017–30.06.2017: The Machine Learning Summer School (Poster)

09.06.2017–11.06.2017: Highlights of Algorithms 2017

12.12.2016–15.12.2016: IEEE International Conference on Data Mining 2016 (Talk)

22.02.–26.02.2016: Indo-German Spring School on Algorithms for Big Data

28.09.–30.09.2015: ACBD 2015 -- Algorithmic Challenges of Big Data

Benchmark Datasets for Graph Classification

I maintain a growing collection of benchmark datasets for supervised graph classification.