Deep Graph Learning will stall without Network Science
Not on the map. Why?
Abstract (arXiv)
Deep graph learning focuses on flexible and generalizable models that learn patterns in an automated fashion. Network science focuses on models and measures revealing the organizational principles of complex systems with explicit assumptions. Both fields share the same goal: to better model and understand patterns in graph-structured data. However, deep graph learning prioritizes empirical performance but ignores fundamental insights from network science. Our position is that deep graph learning will stall without insights from network science. In this position paper, we formulate six Calls for Action to leverage untapped insights from network science to address current issues in deep graph learning, ensuring the field continues to make progress.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 43 of its 80 references that are in the map. First posted on arXiv 3 Feb 2025.
Builds on
43 of 80 references.
References · 43
- 2017Attention Is All You Needcited by 59,932
- 2017Inductive Representation Learning on Large Graphscited by 6,284
- 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,155
- 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
- 2016node2vec: Scalable Feature Learning for Networkscited by 1,913
- 2016Variational Graph Auto-Encoderscited by 1,373
- 2020A Generalization of Transformer Networks to Graphscited by 653
- 2020Temporal Graph Networks for Deep Learning on Dynamic Graphscited by 521
- 2019EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphscited by 443
- 2018From Louvain to Leiden: guaranteeing well-connected communitiescited by 379
- 2021Graph Self-Supervised Learning: A Surveycited by 289
- 2023A Survey on Oversmoothing in Graph Neural Networkscited by 246
31 more
- 2019Causality for Machine Learningcited by 242
- 2020Data Augmentation for Graph Neural Networkscited by 200
- 2021Inductive Representation Learning in Temporal Networks via Causal Anonymous Walkscited by 188
- 2020Graph Clustering with Graph Neural Networkscited by 163
- 2023On Over-Squashing in Message Passing Neural Networks: The Impact of Width, Depth, and Topologycited by 163
- 2023Temporal Graph Benchmark for Machine Learning on Temporal Graphscited by 137
- 2024Position: Graph Foundation Models are Already Herecited by 84
- 2021Graph-MLP: Node Classification without Message Passing in Graphcited by 73
- 2023Evaluating Graph Neural Networks for Link Prediction: Current Pitfalls and New Benchmarkingcited by 69
- 2025Large Language Models Share Representations of Latent Grammatical Concepts Across Typologically Diverse Languagescited by 57
- 2019A Review of Stochastic Block Models and Extensions for Graph Clusteringcited by 46
- 2017Bayesian stochastic blockmodelingcited by 27
- 2015Modern temporal network theory: A colloquiumcited by 23
- 2023Pure Message Passing Can Estimate Common Neighbor for Link Predictioncited by 18
- 2013Memory in network flows and its effects on spreading dynamics and community detectioncited by 17
- 2017Network structure from rich but noisy datacited by 17
- 2024Understanding Heterophily for Graph Neural Networkscited by 15
- 2019Network reconstruction and community detection from dynamicscited by 13
- 2023Half-Hop: A graph upsampling approach for slowing down message passingcited by 13
- 2022Weisfeiler-Lehman goes Dynamic: An Analysis of the Expressive Power of Graph Neural Networks for Attributed and Dynamic Graphscited by 12
- 2013Causality-Driven Slow-Down and Speed-Up of Diffusion in Non-Markovian Temporal Networkscited by 10
- 2017Mapping higher-order network flows in memory and multilayer networks with Infomapcited by 10
- 2022De Bruijn goes Neural: Causality-Aware Graph Neural Networks for Time Series Data on Dynamic Graphscited by 10
- 2015Modeling sequences and temporal networks with dynamic community structurescited by 9
- 2023Network community detection via neural embeddingscited by 7
- 2024Temporal-Aware Evaluation and Learning for Temporal Graph Neural Networkscited by 5
- 2017From Relational Data to Graphs: Inferring Significant Links using Generalized Hypergeometric Ensemblescited by 4
- 2023Using Time-Aware Graph Neural Networks to Predict Temporal Centralities in Dynamic Graphscited by 4
- 2024Link Prediction with Untrained Message Passing Layerscited by 3
- 2014Burstiness and aging in social temporal networkscited by 2
- 2025BN-Pool: Bayesian Nonparametric Pooling for Graphscited by 2
Built on by
Citing papers per year: 2026: 1.
1 paper.