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

arXiv: https://arxiv.org/abs/1906.12192 · HTML: https://mlsanity.com/paper/1906.12192/

## Key facts

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

## Built on by (most cited first, 30 of 75)

- [How Attentive are Graph Attention Networks?](https://mlsanity.com/paper/2105.14491/) (2021)
- [Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs](https://mlsanity.com/paper/2202.04579/) (2022)
- [3D Infomax improves GNNs for Molecular Property Prediction](https://mlsanity.com/paper/2110.04126/) (2021)
- [FoSR: First-order spectral rewiring for addressing oversquashing in GNNs](https://mlsanity.com/paper/2210.11790/) (2022)
- [DRew: Dynamically Rewired Message Passing with Delay](https://mlsanity.com/paper/2305.08018/) (2023)
- [Learning to Extend Molecular Scaffolds with Structural Motifs](https://mlsanity.com/paper/2103.03864/) (2021)
- [A Survey on Graph Representation Learning Methods](https://mlsanity.com/paper/2204.01855/) (2022)
- [Graph Neural Networks for Learning Equivariant Representations of Neural Networks](https://mlsanity.com/paper/2403.12143/) (2024)
- [ForceNet: A Graph Neural Network for Large-Scale Quantum Calculations](https://mlsanity.com/paper/2103.01436/) (2021)
- [GraphWorld: Fake Graphs Bring Real Insights for GNNs](https://mlsanity.com/paper/2203.00112/) (2022)
- [Graph-based Molecular Representation Learning](https://mlsanity.com/paper/2207.04869/) (2022)
- [Shortest Path Networks for Graph Property Prediction](https://mlsanity.com/paper/2206.01003/) (2022)
- [High-Level Synthesis Performance Prediction using GNNs: Benchmarking, Modeling, and Advancing](https://mlsanity.com/paper/2201.06848/) (2022)
- [Probabilistically Rewired Message-Passing Neural Networks](https://mlsanity.com/paper/2310.02156/) (2023)
- [Source-Free Progressive Graph Learning for Open-Set Domain Adaptation](https://mlsanity.com/paper/2202.06174/) (2022)
- [Directional Message Passing on Molecular Graphs via Synthetic Coordinates](https://mlsanity.com/paper/2111.04718/) (2021)
- [Adaptive Message Passing: A General Framework to Mitigate Oversmoothing, Oversquashing, and Underreaching](https://mlsanity.com/paper/2312.16560/) (2023)
- [Large-scale graph representation learning with very deep GNNs and self-supervision](https://mlsanity.com/paper/2107.09422/) (2021)
- [Meta-Inductive Node Classification across Graphs](https://mlsanity.com/paper/2105.06725/) (2021)
- [Homomorphism Counts for Graph Neural Networks: All About That Basis](https://mlsanity.com/paper/2402.08595/) (2024)
- [Learning Topology-Specific Experts for Molecular Property Prediction](https://mlsanity.com/paper/2302.13693/) (2023)
- [V2-SAM: Marrying SAM2 with Multi-Prompt Experts for Cross-View Object Correspondence](https://mlsanity.com/paper/2511.20886/) (2025)
- [PlanE: Representation Learning over Planar Graphs](https://mlsanity.com/paper/2307.01180/) (2023)
- [Neural Relational Inference with Efficient Message Passing Mechanisms](https://mlsanity.com/paper/2101.09486/) (2021)
- [Node-wise Localization of Graph Neural Networks](https://mlsanity.com/paper/2110.14322/) (2021)
- [PANDA: Expanded Width-Aware Message Passing Beyond Rewiring](https://mlsanity.com/paper/2406.03671/) (2024)
- [From Screens to Scenes: A Survey of Embodied AI in Healthcare](https://mlsanity.com/paper/2501.07468/) (2025)
- [PolyNet: Polynomial Neural Network for 3D Shape Recognition with PolyShape Representation](https://mlsanity.com/paper/2110.07882/) (2021)
- [RegExplainer: Generating Explanations for Graph Neural Networks in Regression Tasks](https://mlsanity.com/paper/2307.07840/) (2023)
- [Almost Surely Asymptotically Constant Graph Neural Networks](https://mlsanity.com/paper/2403.03880/) (2024)

## 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.