mlsanityData to 14 Oct 2026

GNN-FiLM: Graph Neural Networks with Feature-wise Linear Modulation

arXiv 1906.12192 ↗First posted 28 Jun 2019cs.LG stat.MLcited by 75

Not on the map. Why?

Abstract (arXiv)

This paper presents a new Graph Neural Network (GNN) type using feature-wise linear modulation (FiLM). Many standard GNN variants propagate information along the edges of a graph by computing "messages" based only on the representation of the source of each edge. In GNN-FiLM, the representation of the target node of an edge is additionally used to compute a transformation that can be applied to all incoming messages, allowing feature-wise modulation of the passed information. Results of experiments comparing different GNN architectures on three tasks from the literature are presented, based on re-implementations of baseline methods. Hyperparameters for all methods were found using extensive search, yielding somewhat surprising results: differences between baseline models are smaller than reported in the literature. Nonetheless, GNN-FiLM outperforms baseline methods on a regression task on molecular graphs and performs competitively on other tasks.

Key facts. Cited by 75 papers in the map (data through 14 Oct 2026). First posted on arXiv 28 Jun 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 14; 2022: 13; 2023: 12; 2024: 13; 2025: 13; 2026: 10.

75 papers.

Sort:

By area:

  1. 2021How Attentive are Graph Attention Networks?cited by 835
  2. 2022Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNscited by 214
  3. 20213D Infomax improves GNNs for Molecular Property Predictioncited by 146
  4. 2022FoSR: First-order spectral rewiring for addressing oversquashing in GNNscited by 105
  5. 2023DRew: Dynamically Rewired Message Passing with Delaycited by 82
  6. 2021Learning to Extend Molecular Scaffolds with Structural Motifscited by 71
  7. 2022A Survey on Graph Representation Learning Methodscited by 66
  8. 2024Graph Neural Networks for Learning Equivariant Representations of Neural Networkscited by 59
  9. 2021ForceNet: A Graph Neural Network for Large-Scale Quantum Calculationscited by 58
  10. 2022GraphWorld: Fake Graphs Bring Real Insights for GNNscited by 56
  11. 2022Graph-based Molecular Representation Learningcited by 51
  12. 2022Shortest Path Networks for Graph Property Predictioncited by 46
38 more
  1. 2022High-Level Synthesis Performance Prediction using GNNs: Benchmarking, Modeling, and Advancingcited by 26
  2. 2023Probabilistically Rewired Message-Passing Neural Networkscited by 26
  3. 2022Source-Free Progressive Graph Learning for Open-Set Domain Adaptationcited by 25
  4. 2021Directional Message Passing on Molecular Graphs via Synthetic Coordinatescited by 24
  5. 2023Adaptive Message Passing: A General Framework to Mitigate Oversmoothing, Oversquashing, and Underreachingcited by 24
  6. 2021Large-scale graph representation learning with very deep GNNs and self-supervisioncited by 18
  7. 2021Meta-Inductive Node Classification across Graphscited by 16
  8. 2024Homomorphism Counts for Graph Neural Networks: All About That Basiscited by 16
  9. 2023Learning Topology-Specific Experts for Molecular Property Predictioncited by 15
  10. 2025V2-SAM: Marrying SAM2 with Multi-Prompt Experts for Cross-View Object Correspondencecited by 14
  11. 2023PlanE: Representation Learning over Planar Graphscited by 11
  12. 2021Neural Relational Inference with Efficient Message Passing Mechanismscited by 10
  13. 2021Node-wise Localization of Graph Neural Networkscited by 10
  14. 2024PANDA: Expanded Width-Aware Message Passing Beyond Rewiringcited by 10
  15. 2025From Screens to Scenes: A Survey of Embodied AI in Healthcarecited by 10
  16. 2021PolyNet: Polynomial Neural Network for 3D Shape Recognition with PolyShape Representationcited by 9
  17. 2023RegExplainer: Generating Explanations for Graph Neural Networks in Regression Taskscited by 9
  18. 2024Almost Surely Asymptotically Constant Graph Neural Networkscited by 7
  19. 2024Homomorphism Counts as Structural Encodings for Graph Learningcited by 7
  20. 2021Optimizing Sparse Matrix Multiplications for Graph Neural Networkscited by 6
  21. 2022Automatic Relation-aware Graph Network Proliferationcited by 6
  22. 2023Examining the Effects of Degree Distribution and Homophily in Graph Learning Modelscited by 5
  23. 2025DiffNMR: Diffusion Models for Nuclear Magnetic Resonance Spectra Elucidationcited by 5
  24. 2023Document-Level Multi-Event Extraction with Event Proxy Nodes and Hausdorff Distance Minimizationcited by 4
  25. 2023ColdNAS: Search to Modulate for User Cold-Start Recommendationcited by 4
  26. 2023PACIA: Parameter-Efficient Adapter for Few-Shot Molecular Property Predictioncited by 4
  27. 2024Efficacy of Various Large Language Models in Generating Smart Contractscited by 4
  28. 2025Aggregate to Adapt: Node-Centric Aggregation for Multi-Source-Free Graph Domain Adaptationcited by 4
  29. 2023Inductive biases in deep learning models for weather predictioncited by 3
  30. 2024PF-GNN: Differentiable particle filtering based approximation of universal graph representationscited by 3
  31. 2025Probabilistic Predictions of Process-Induced Deformation in Carbon/Epoxy Composites Using a Deep Operator Networkcited by 3
  32. 2021Edge-featured Graph Neural Architecture Searchcited by 2
  33. 2022Embedding Graphs on Grassmann Manifoldcited by 2
  34. 2022Deep Surrogate Docking: Accelerating Automated Drug Discovery with Graph Neural Networkscited by 2
  35. 2023CAT: A Causally Graph Attention Network for Trimming Heterophilic Graphcited by 2
  36. 2024NetDiff: Graph Diffusion with Improved Global Capabilities to Generate and Update Mobile Network Topologiescited by 2
  37. 2024MGM: Global Understanding of Audience Overlap Graphs for Predicting the Factuality and the Bias of News Mediacited by 2
  38. 2025Rapid training of Hamiltonian graph networks using random featurescited by 2

50 most cited of 75 All 75 (JSON)