# Domain Generalization Deep Graph Transformation

arXiv: https://arxiv.org/abs/2305.11389 · HTML: https://mlsanity.com/paper/2305.11389/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 35 references that are in the map.
- First posted on arXiv 19 May 2023.

## Builds on (most cited first, 24 of 24)

- [Variational Graph Auto-Encoders](https://mlsanity.com/paper/1611.07308/) (2016)
- [Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting](https://mlsanity.com/paper/1709.04875/) (2017)
- [HyperNetworks](https://mlsanity.com/paper/1609.09106/) (2016)
- [Interaction Networks for Learning about Objects, Relations and Physics](https://mlsanity.com/paper/1612.00222/) (2016)
- [Domain Generalization via Model-Agnostic Learning of Semantic Features](https://mlsanity.com/paper/1910.13580/) (2019)
- [HyperStyle: StyleGAN Inversion with HyperNetworks for Real Image Editing](https://mlsanity.com/paper/2111.15666/) (2021)
- [DLOW: Domain Flow for Adaptation and Generalization](https://mlsanity.com/paper/1812.05418/) (2018)
- [Handling Distribution Shifts on Graphs: An Invariance Perspective](https://mlsanity.com/paper/2202.02466/) (2022)
- [AdaRNN: Adaptive Learning and Forecasting of Time Series](https://mlsanity.com/paper/2108.04443/) (2021)
- [Continual Model-Based Reinforcement Learning with Hypernetworks](https://mlsanity.com/paper/2009.11997/) (2020)
- [Meta-Learning for Domain Generalization in Semantic Parsing](https://mlsanity.com/paper/2010.11988/) (2020)
- [Compound Domain Generalization via Meta-Knowledge Encoding](https://mlsanity.com/paper/2203.13006/) (2022)
- [Temporal Domain Generalization with Drift-Aware Dynamic Neural Networks](https://mlsanity.com/paper/2205.10664/) (2022)
- [HyperShot: Few-Shot Learning by Kernel HyperNetworks](https://mlsanity.com/paper/2203.11378/) (2022)
- [Hypernetworks for Zero-shot Transfer in Reinforcement Learning](https://mlsanity.com/paper/2211.15457/) (2022)
- [Example-based Hypernetworks for Out-of-Distribution Generalization](https://mlsanity.com/paper/2203.14276/) (2022)
- [Learn to Expect the Unexpected: Probably Approximately Correct Domain Generalization](https://mlsanity.com/paper/2002.05660/) (2020)
- [Deep Graph Translation](https://mlsanity.com/paper/1805.09980/) (2018)
- [HyperPELT: Unified Parameter-Efficient Language Model Tuning for Both Language and Vision-and-Language Tasks](https://mlsanity.com/paper/2203.03878/) (2022)
- [Multi-objective Deep Data Generation with Correlated Property Control](https://mlsanity.com/paper/2210.01796/) (2022)
- [HyperNetworks with statistical filtering for defending adversarial examples](https://mlsanity.com/paper/1711.01791/) (2017)
- [HMOE: Hypernetwork-based Mixture of Experts for Domain Generalization](https://mlsanity.com/paper/2211.08253/) (2022)
- [Deep Multi-attributed Graph Translation with Node-Edge Co-evolution](https://mlsanity.com/paper/2003.09945/) (2020)
- [Meta Graph Attention on Heterogeneous Graph with Node-Edge Co-evolution](https://mlsanity.com/paper/2010.04554/) (2020)

## Built on by (most cited first, 1 of 1)

- [R-Mixup: Riemannian Mixup for Biological Networks](https://mlsanity.com/paper/2306.02532/) (2023)

## Abstract (arXiv)

Graph transformation that predicts graph transition from one mode to another is an important and common problem. Despite much progress in developing advanced graph transformation techniques in recent years, the fundamental assumption typically required in machine-learning models that the testing and training data preserve the same distribution does not always hold. As a result, domain generalization graph transformation that predicts graphs not available in the training data is under-explored, with multiple key challenges to be addressed including (1) the extreme space complexity when training on all input-output mode combinations, (2) difference of graph topologies between the input and the output modes, and (3) how to generalize the model to (unseen) target domains that are not in the training data. To fill the gap, we propose a multi-input, multi-output, hypernetwork-based graph neural network (MultiHyperGNN) that employs a encoder and a decoder to encode topologies of both input and output modes and semi-supervised link prediction to enhance the graph transformation task. Instead of training on all mode combinations, MultiHyperGNN preserves a constant space complexity with the encoder and the decoder produced by two novel hypernetworks. Comprehensive experiments show that MultiHyperGNN has a superior performance than competing models in both prediction and domain generalization tasks.