Position: Future Directions in the Theory of Graph Machine Learning

Authors: Christopher Morris, Fabrizio Frasca, Nadav Dym, Haggai Maron, Ismail Ilkan Ceylan, Ron Levie, Derek Lim, Michael M. Bronstein, Martin Grohe, Stefanie Jegelka

ICML 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical In this position paper, we argue that the graph machine learning community needs to shift its attention to developing a balanced theory of graph machine learning, focusing on a more thorough understanding of the interplay of expressive power, generalization, and optimization.
Researcher Affiliation Collaboration 1RWTH Aachen University 2Technion Israel Institute of Technology 3NVIDIA Research 4University of Oxford 5MIT 6TU Munich.
Pseudocode No The paper does not contain any pseudocode or algorithm blocks.
Open Source Code No The paper mentions existing open-source libraries (PYTORCH GEOMETRIC, DGL) and refers to code released by other authors ('Wang & Zhang (2023a) took a first step in this direction by providing open-source implementations'), but it does not provide concrete access to source code for the concepts or analyses described in this position paper.
Open Datasets No This is a position paper that does not conduct experiments, therefore it does not provide access information for a dataset used for training. It mentions datasets like BREC as examples from other work but does not use them itself.
Dataset Splits No This is a position paper that does not conduct experiments, therefore it does not provide specific dataset split information for validation.
Hardware Specification No This is a position paper that does not conduct experiments and therefore does not provide specific hardware details.
Software Dependencies No This is a position paper that does not conduct experiments and therefore does not provide specific ancillary software details with version numbers.
Experiment Setup No This is a position paper that does not conduct experiments and therefore does not provide specific experimental setup details.