TY - JOUR
T1 - Position
T2 - 41st International Conference on Machine Learning, ICML 2024
AU - Morris, Christopher
AU - Frasca, Fabrizio
AU - Dym, Nadav
AU - Maron, Haggai
AU - Ceylan, Ismail Ilkan
AU - Levie, Ron
AU - Lim, Derek
AU - Bronstein, Michael
AU - Grohe, Martin
AU - Jegelka, Stefanie
N1 - Publisher Copyright:
Copyright 2024 by the author(s)
PY - 2024
Y1 - 2024
N2 - Machine learning on graphs, especially using graph neural networks (GNNs), has seen a surge in interest due to the wide availability of graph data across a broad spectrum of disciplines, from life to social and engineering sciences. Despite their practical success, our theoretical understanding of the properties of GNNs remains highly incomplete. Recent theoretical advancements primarily focus on elucidating the coarse-grained expressive power of GNNs, predominantly employing combinatorial techniques. However, these studies do not perfectly align with practice, particularly in understanding the generalization behavior of GNNs when trained with stochastic first-order optimization techniques. 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.
AB - Machine learning on graphs, especially using graph neural networks (GNNs), has seen a surge in interest due to the wide availability of graph data across a broad spectrum of disciplines, from life to social and engineering sciences. Despite their practical success, our theoretical understanding of the properties of GNNs remains highly incomplete. Recent theoretical advancements primarily focus on elucidating the coarse-grained expressive power of GNNs, predominantly employing combinatorial techniques. However, these studies do not perfectly align with practice, particularly in understanding the generalization behavior of GNNs when trained with stochastic first-order optimization techniques. 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.
UR - http://www.scopus.com/inward/record.url?scp=85203817935&partnerID=8YFLogxK
M3 - Conference article
AN - SCOPUS:85203817935
SN - 2640-3498
VL - 235
SP - 36294
EP - 36307
JO - Proceedings of Machine Learning Research
JF - Proceedings of Machine Learning Research
Y2 - 21 July 2024 through 27 July 2024
ER -