# Building Deep Graph Predictors with Graph Imitation Learning

arXiv: https://arxiv.org/abs/2601.15133 · HTML: https://mlsanity.com/paper/2601.15133/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 35 references that are in the map.
- First posted on arXiv 21 Jan 2026.

## Builds on (most cited first, 25 of 25)

- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [Understanding deep learning requires rethinking generalization](https://mlsanity.com/paper/1611.03530/) (2016)
- [Variational Graph Auto-Encoders](https://mlsanity.com/paper/1611.07308/) (2016)
- [Junction Tree Variational Autoencoder for Molecular Graph Generation](https://mlsanity.com/paper/1802.04364/) (2018)
- [DiGress: Discrete Denoising diffusion for graph generation](https://mlsanity.com/paper/2209.14734/) (2022)
- [Scene Graph Generation by Iterative Message Passing](https://mlsanity.com/paper/1701.02426/) (2017)
- [GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models](https://mlsanity.com/paper/1802.08773/) (2018)
- [GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoders](https://mlsanity.com/paper/1802.03480/) (2018)
- [Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation](https://mlsanity.com/paper/1806.02473/) (2018)
- [Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equations](https://mlsanity.com/paper/2202.02514/) (2022)
- [Efficient Graph Generation with Graph Recurrent Attention Networks](https://mlsanity.com/paper/1910.00760/) (2019)
- [Learning Deep Generative Models of Graphs](https://mlsanity.com/paper/1803.03324/) (2018)
- [GraphDF: A Discrete Flow Model for Molecular Graph Generation](https://mlsanity.com/paper/2102.01189/) (2021)
- [GraphNVP: An Invertible Flow Model for Generating Molecular Graphs](https://mlsanity.com/paper/1905.11600/) (2019)
- [Graphite: Iterative Generative Modeling of Graphs](https://mlsanity.com/paper/1803.10459/) (2018)
- [RoadTracer: Automatic Extraction of Road Networks from Aerial Images](https://mlsanity.com/paper/1802.03680/) (2018)
- [SoftSort: A Continuous Relaxation for the argsort Operator](https://mlsanity.com/paper/2006.16038/) (2020)
- [MolScribe: Robust Molecular Structure Recognition with Image-To-Graph Generation](https://mlsanity.com/paper/2205.14311/) (2022)
- [T2SG: Traffic Topology Scene Graph for Topology Reasoning in Autonomous Driving](https://mlsanity.com/paper/2411.18894/) (2024)
- [Molecular Structure Extraction From Documents Using Deep Learning](https://mlsanity.com/paper/1802.04903/) (2018)
- [MolGrapher: Graph-based Visual Recognition of Chemical Structures](https://mlsanity.com/paper/2308.12234/) (2023)
- [Permutation-Invariant Variational Autoencoder for Graph-Level Representation Learning](https://mlsanity.com/paper/2104.09856/) (2021)
- [Learning and Aggregating Lane Graphs for Urban Automated Driving](https://mlsanity.com/paper/2302.06175/) (2023)
- [The quest for the GRAph Level autoEncoder (GRALE)](https://mlsanity.com/paper/2505.22109/) (2025)
- [Any2Graph: Deep End-To-End Supervised Graph Prediction With An Optimal Transport Loss](https://mlsanity.com/paper/2402.12269/) (2024)

## Abstract (arXiv)

Recent years have seen substantial progress in neural generation of text, images, and audio, supported by mature training pipelines and large-scale optimization. For graphs, however, comparable progress has been more limited. We attribute this gap to graph-specific optimization and representation challenges that undermine the effectiveness of training neural networks with backpropagation and gradient descent. We argue that representing graphs on a fixed-size Euclidean grid, as is common in recently proposed models for supervised graph prediction, may not be the optimal choice in these settings. To support our view, we provide an analysis of neural graph generation methods and identify theoretical challenges that lead to pitfalls when training neural networks to produce graphs as their output. Motivated by this analysis, we introduce GRAph~Imitation~Learning~(GRAIL), a framework for training neural networks in supervised settings in which the supervision signal is a graph. GRAIL generates graphs sequentially through a Markov decision process over embeddings of partial graphs, thereby avoiding the representation issues associated with fixed-size grid graph representations. We empirically show that GRAIL achieves competitive results on supervised graph prediction across a comprehensive suite of 18 benchmarks, matching or surpassing state-of-the-art methods in several settings.