Timezone: »
Graph pooling is a central component of a myriad of graph neural network (GNN) architectures. As an inheritance from traditional CNNs, most approaches formulate graph pooling as a cluster assignment problem, extending the idea of local patches in regular grids to graphs. Despite the wide adherence to this design choice, no work has rigorously evaluated its influence on the success of GNNs. In this paper, we build upon representative GNNs and introduce variants that challenge the need for locality-preserving representations, either using randomization or clustering on the complement graph. Strikingly, our experiments demonstrate that using these variants does not result in any decrease in performance. To understand this phenomenon, we study the interplay between convolutional layers and the subsequent pooling ones. We show that the convolutions play a leading role in the learned representations. In contrast to the common belief, local pooling is not responsible for the success of GNNs on relevant and widely-used benchmarks.
Author Information
Diego Mesquita (Aalto University)
Amauri Souza (Federal Institute of Ceara)
Samuel Kaski (Aalto University and University of Manchester)
More from the Same Authors
-
2022 : Deep Mahalanobis Gaussian Process »
Daniel Augusto de Souza · Diego Mesquita · César Lincoln Mattos · João Paulo Gomes -
2022 : Modular Flows: Differential Molecular Generation »
Yogesh Verma · Samuel Kaski · Markus Heinonen · Vikas Garg -
2022 : Targeted Causal Elicitation »
Nazaal Ibrahim · ST John · Zhigao Guo · Samuel Kaski -
2022 : More trustworthy Bayesian optimization of materials properties by adding human into the loop »
Armi Tiihonen · Louis Filstroff · Petrus Mikkola · Emma Lehto · Samuel Kaski · Milica Todorović · Patrick Rinke -
2022 : Provably expressive temporal graph networks »
Amauri Souza · Diego Mesquita · Samuel Kaski · Vikas Garg -
2022 : Modular Flows: Differential Molecular Generation »
Yogesh Verma · Samuel Kaski · Markus Heinonen · Vikas Garg -
2022 : Differentiable User Models »
Alex Hämäläinen · Mustafa Mert Çelikok · Samuel Kaski -
2023 : Preferential Heteroscedastic Bayesian Optimization with Informative Noise Priors »
Marshal Sinaga · Julien Martinelli · Samuel Kaski -
2023 : Learning relevant contextual variables within Bayesian optimization »
Julien Martinelli · Ayush Bharti · Armi Tiihonen · Louis Filstroff · ST John · Sabina Sloman · Patrick Rinke · Samuel Kaski -
2023 : Leveraging expert feedback to align proxy and ground truth rewards in goal-oriented molecular generation »
Julien Martinelli · Yasmine Nahal · Duong Lê · Ola Engkvist · Samuel Kaski -
2023 Poster: Practical Equivariances via Relational Conditional Neural Processes »
Daolang Huang · Manuel Haussmann · Ulpu Remes · ST John · Grégoire Clarté · Kevin Sebastian Luck · Samuel Kaski · Luigi Acerbi -
2023 Poster: Compositional Sculpting of Iterative Generative Processes »
Timur Garipov · Sebastiaan De Peuter · Ge Yang · Vikas Garg · Samuel Kaski · Tommi Jaakkola -
2023 Poster: Going beyond persistent homology using persistent homology »
Johanna Immonen · Amauri Souza · Vikas Garg -
2023 Oral: Going beyond persistent homology using persistent homology »
Johanna Immonen · Amauri Souza · Vikas Garg -
2023 Poster: Learning Robust Statistics for Simulation-based Inference under Model Misspecification »
Daolang Huang · Ayush Bharti · Amauri Souza · Luigi Acerbi · Samuel Kaski -
2022 : Panel Discussion »
Cynthia Rudin · Dan Bohus · Brenna Argall · Alison Gopnik · Igor Mordatch · Samuel Kaski -
2022 : Collaborative AI for assisting virtual laboratories »
Samuel Kaski -
2022 : Noise-Aware Statistical Inference with Differentially Private Synthetic Data »
Ossi Räisä · Joonas Jälkö · Antti Honkela · Samuel Kaski -
2022 : HAPNEST: An efficient tool for generating large-scale genetics datasets from limited training data »
Sophie Wharrie · Zhiyu Yang · Vishnu Raj · Remo Monti · Rahul Gupta · Ying Wang · Alicia Martin · Luke O'Connor · Samuel Kaski · Pekka Marttinen · Pier Palamara · Christoph Lippert · Andrea Ganna -
2022 Poster: Modular Flows: Differential Molecular Generation »
Yogesh Verma · Samuel Kaski · Markus Heinonen · Vikas Garg -
2022 Poster: Deconfounded Representation Similarity for Comparison of Neural Networks »
Tianyu Cui · Yogesh Kumar · Pekka Marttinen · Samuel Kaski -
2022 Poster: Provably expressive temporal graph networks »
Amauri Souza · Diego Mesquita · Samuel Kaski · Vikas Garg -
2021 Poster: De-randomizing MCMC dynamics with the diffusion Stein operator »
Zheyang Shen · Markus Heinonen · Samuel Kaski -
2019 : Coffee/Poster session 1 »
Shiro Takagi · Khurram Javed · Johanna Sommer · Amr Sharaf · Pierluca D'Oro · Ying Wei · Sivan Doveh · Colin White · Santiago Gonzalez · Cuong Nguyen · Mao Li · Tianhe Yu · Tiago Ramalho · Masahiro Nomura · Ahsan Alvi · Jean-Francois Ton · W. Ronny Huang · Jessica Lee · Sebastian Flennerhag · Michael Zhang · Abram Friesen · Paul Blomstedt · Alina Dubatovka · Sergey Bartunov · Subin Yi · Iaroslav Shcherbatyi · Christian Simon · Zeyuan Shang · David MacLeod · Lu Liu · Liam Fowl · Diego Mesquita · Deirdre Quillen -
2019 Poster: Machine Teaching of Active Sequential Learners »
Tomi Peltola · Mustafa Mert Çelikok · Pedram Daee · Samuel Kaski -
2017 Poster: Non-Stationary Spectral Kernels »
Sami Remes · Markus Heinonen · Samuel Kaski -
2017 Poster: Differentially private Bayesian learning on distributed data »
Mikko Heikkilä · Eemil Lagerspetz · Samuel Kaski · Kana Shimizu · Sasu Tarkoma · Antti Honkela -
2014 Workshop: Machine Learning in Computational Biology »
Oliver Stegle · Sara Mostafavi · Anna Goldenberg · Su-In Lee · Michael Leung · Anshul Kundaje · Mark B Gerstein · Martin Renqiang Min · Hannes Bretschneider · Francesco Paolo Casale · Loïc Schwaller · Amit G Deshwar · Benjamin A Logsdon · Yuanyang Zhang · Ali Punjani · Derek C Aguiar · Samuel Kaski