mlsanityData to 7 Oct 2026

Rethinking the Setting of Semi-supervised Learning on Graphs

arXiv 2205.14403 ↗First posted 28 May 2022cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

We argue that the present setting of semisupervised learning on graphs may result in unfair comparisons, due to its potential risk of over-tuning hyper-parameters for models. In this paper, we highlight the significant influence of tuning hyper-parameters, which leverages the label information in the validation set to improve the performance. To explore the limit of over-tuning hyperparameters, we propose ValidUtil, an approach to fully utilize the label information in the validation set through an extra group of hyper-parameters. With ValidUtil, even GCN can easily get high accuracy of 85.8% on Cora. To avoid over-tuning, we merge the training set and the validation set and construct an i.i.d. graph benchmark (IGB) consisting of 4 datasets. Each dataset contains 100 i.i.d. graphs sampled from a large graph to reduce the evaluation variance. Our experiments suggest that IGB is a more stable benchmark than previous datasets for semisupervised learning on graphs.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 19 of its 30 references that are in the map. First posted on arXiv 28 May 2022.

Builds on

19 of 30 references.

References · 19

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2017Graph Attention Networkscited by 8,854
  4. 2017Inductive Representation Learning on Large Graphscited by 6,284
  5. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,414
  6. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
  7. 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 987
  8. 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 970
  9. 2020Simple and Deep Graph Convolutional Networkscited by 857
  10. 2019GraphSAINT: Graph Sampling Based Inductive Learning Methodcited by 618
  11. 2019Multi-scale Attributed Node Embeddingcited by 543
  12. 2019MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixingcited by 442
7 more
  1. 2019Diffusion Improves Graph Learningcited by 414
  2. 2020Graph Random Neural Network for Semi-Supervised Learning on Graphscited by 213
  3. 2020Combining Label Propagation and Simple Models Out-performs Graph Neural Networkscited by 199
  4. 2021Are we really making much progress? Revisiting, benchmarking, and refining heterogeneous graph neural networkscited by 176
  5. 2020Understanding Negative Sampling in Graph Representation Learningcited by 66
  6. 2021Pairwise Learning for Neural Link Predictioncited by 23
  7. 2021FewNLU: Benchmarking State-of-the-Art Methods for Few-Shot Natural Language Understandingcited by 17

Built on by

Not cited yet.