mlsanityData to 7 Oct 2026

Domain Generalization Deep Graph Transformation

arXiv 2305.11389 ↗First posted 19 May 2023cs.LG cs.AIcited by 1

Not on the map. Why?

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.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 24 of its 35 references that are in the map. First posted on arXiv 19 May 2023.

Builds on

24 of 35 references.

References · 24

  1. 2016Variational Graph Auto-Encoderscited by 1,373
  2. 2017Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecastingcited by 1,125
  3. 2016HyperNetworkscited by 1,003
  4. 2016Interaction Networks for Learning about Objects, Relations and Physicscited by 503
  5. 2019Domain Generalization via Model-Agnostic Learning of Semantic Featurescited by 405
  6. 2021HyperStyle: StyleGAN Inversion with HyperNetworks for Real Image Editingcited by 208
  7. 2018DLOW: Domain Flow for Adaptation and Generalizationcited by 176
  8. 2022Handling Distribution Shifts on Graphs: An Invariance Perspectivecited by 163
  9. 2021AdaRNN: Adaptive Learning and Forecasting of Time Seriescited by 120
  10. 2020Continual Model-Based Reinforcement Learning with Hypernetworkscited by 41
  11. 2020Meta-Learning for Domain Generalization in Semantic Parsingcited by 41
  12. 2022Compound Domain Generalization via Meta-Knowledge Encodingcited by 40
12 more
  1. 2022Temporal Domain Generalization with Drift-Aware Dynamic Neural Networkscited by 32
  2. 2022HyperShot: Few-Shot Learning by Kernel HyperNetworkscited by 24
  3. 2022Hypernetworks for Zero-shot Transfer in Reinforcement Learningcited by 18
  4. 2022Example-based Hypernetworks for Out-of-Distribution Generalizationcited by 16
  5. 2020Learn to Expect the Unexpected: Probably Approximately Correct Domain Generalizationcited by 14
  6. 2018Deep Graph Translationcited by 12
  7. 2022HyperPELT: Unified Parameter-Efficient Language Model Tuning for Both Language and Vision-and-Language Taskscited by 12
  8. 2022Multi-objective Deep Data Generation with Correlated Property Controlcited by 10
  9. 2017HyperNetworks with statistical filtering for defending adversarial examplescited by 8
  10. 2022HMOE: Hypernetwork-based Mixture of Experts for Domain Generalizationcited by 8
  11. 2020Deep Multi-attributed Graph Translation with Node-Edge Co-evolutioncited by 6
  12. 2020Meta Graph Attention on Heterogeneous Graph with Node-Edge Co-evolutioncited by 1

Built on by

Cited by year

Citing papers per year: 2023: 1.

1 paper.

  1. 2023R-Mixup: Riemannian Mixup for Biological Networkscited by 8