mlsanityData to 7 Oct 2026

Lying Graph Convolution: Learning to Lie for Node Classification Tasks

arXiv 2405.01247 ↗First posted 2 May 2024cs.LG cs.SIcited by 0

Not on the map. Why?

Abstract (arXiv)

In the context of machine learning for graphs, many researchers have empirically observed that Deep Graph Networks (DGNs) perform favourably on node classification tasks when the graph structure is homophilic (ie adjacent nodes are similar). In this paper, we introduce Lying-GCN, a new DGN inspired by opinion dynamics that can adaptively work in both the heterophilic and the homophilic setting. At each layer, each agent (node) shares its own opinions (node embeddings) with its neighbours. Instead of sharing its opinion directly as in GCN, we introduce a mechanism which allows agents to lie. Such a mechanism is adaptive, thus the agents learn how and when to lie according to the task that should be solved. We provide a characterisation of our proposal in terms of dynamical systems, by studying the spectral property of the coefficient matrix of the system. While the steady state of the system collapses to zero, we believe the lying mechanism is still usable to solve node classification tasks. We empirically prove our belief on both synthetic and real-world datasets, by showing that the lying mechanism allows to increase the performances in the heterophilic setting without harming the results in the homophilic one.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 25 of its 43 references that are in the map. First posted on arXiv 2 May 2024.

Builds on

25 of 43 references.

References · 25

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2017Graph Attention Networkscited by 8,854
  4. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  5. 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,099
  6. 2020Simple and Deep Graph Convolutional Networkscited by 857
  7. 2020Geom-GCN: Geometric Graph Convolutional Networkscited by 821
  8. 2019Graph Neural Networks for Social Recommendationcited by 711
  9. 2019Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological Viewcited by 544
  10. 2021Beyond Low-frequency Information in Graph Convolutional Networkscited by 361
  11. 2023A critical look at the evaluation of GNNs under heterophily: Are we really making progress?cited by 332
  12. 2022Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNscited by 208
13 more
  1. 2021Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networkscited by 182
  2. 2021Is Homophily a Necessity for Graph Neural Networks?cited by 182
  3. 2022Graph neural networks for materials science and chemistrycited by 181
  4. 2019A Gentle Introduction to Deep Learning for Graphscited by 107
  5. 2019GNN-FiLM: Graph Neural Networks with Feature-wise Linear Modulationcited by 75
  6. 2021Dissecting the Diffusion Process in Linear Graph Convolutional Networkscited by 58
  7. 2022Anti-Symmetric DGN: a stable architecture for Deep Graph Networkscited by 58
  8. 2021Simplifying approach to Node Classification in Graph Neural Networkscited by 56
  9. 2022High-Order Pooling for Graph Neural Networks with Tensor Decompositioncited by 24
  10. 2022Beyond Real-world Benchmark Datasets: An Empirical Study of Node Classification with GNNscited by 23
  11. 20222-hop Neighbor Class Similarity (2NCS): A graph structural metric indicative of graph neural network performancecited by 8
  12. 2023Investigating the Interplay between Features and Structures in Graph Learningcited by 5
  13. 2020Learning from Non-Binary Constituency Trees via Tensor Decompositioncited by 3

Built on by

Not cited yet.