• Corpus ID: 239998578

Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods

@article{Lim2021LargeSL,
  title={Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods},
  author={Derek Lim and Felix Hohne and Xiuyu Li and Sijia Huang and Vaishnavi Gupta and Omkar Bhalerao and Ser-Nam Lim},
  journal={ArXiv},
  year={2021},
  volume={abs/2110.14446}
}
  • Derek Lim, Felix Hohne, +4 authors Ser-Nam Lim
  • Published 27 October 2021
  • Computer Science, Mathematics
  • ArXiv
Many widely used datasets for graph machine learning tasks have generally been homophilous, where nodes with similar labels connect to each other. Recently, new Graph Neural Networks (GNNs) have been developed that move beyond the homophily regime; however, their evaluation has often been conducted on small graphs with limited application domains. We collect and introduce diverse nonhomophilous datasets from a variety of application areas that have up to 384x more nodes and 1398x more edges… 
Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networks
TLDR
This work theoretically characterize the connections between heterophily and oversmoothing, and designs a model that addresses the discrepancy in features and degrees between neighbors by incorporating signed messages and learned degree corrections.

References

SHOWING 1-10 OF 91 REFERENCES
Scaling Graph Neural Networks with Approximate PageRank
TLDR
The PPRGo model is presented, which utilizes an efficient approximation of information diffusion in GNNs resulting in significant speed gains while maintaining state-of-the-art prediction performance, and the practical application of PPR go to solve large-scale node classification problems at Google.
Inductive Representation Learning on Large Graphs
TLDR
GraphSAGE is presented, a general, inductive framework that leverages node feature information (e.g., text attributes) to efficiently generate node embeddings for previously unseen data and outperforms strong baselines on three inductive node-classification benchmarks.
Pitfalls of Graph Neural Network Evaluation
TLDR
This paper performs a thorough empirical evaluation of four prominent GNN models and suggests that simpler GNN architectures are able to outperform the more sophisticated ones if the hyperparameters and the training procedure are tuned fairly for all models.
Representation Learning on Graphs with Jumping Knowledge Networks
TLDR
This work explores an architecture -- jumping knowledge (JK) networks -- that flexibly leverages, for each node, different neighborhood ranges to enable better structure-aware representation in graphs.
GraphSAINT: Graph Sampling Based Inductive Learning Method
TLDR
GraphSAINT is proposed, a graph sampling based inductive learning method that improves training efficiency in a fundamentally different way and can decouple the sampling process from the forward and backward propagation of training, and extend GraphSAINT with other graph samplers and GCN variants.
Predict then Propagate: Graph Neural Networks meet Personalized PageRank
TLDR
This paper uses the relationship between graph convolutional networks (GCN) and PageRank to derive an improved propagation scheme based on personalized PageRank, and constructs a simple model, personalized propagation of neural predictions (PPNP), and its fast approximation, APPNP.
How to Find Your Friendly Neighborhood: Graph Attention Design with Self-Supervision
TLDR
A self-supervised graph attention network (SuperGAT) is proposed, an improved graph attention model for noisy graphs that exploits two attention forms compatible with a self- supervised task to predict edges, whose presence and absence contain the inherent information about the importance of the relationships between nodes.
Combining Label Propagation and Simple Models Out-performs Graph Neural Networks
TLDR
This work shows that for many standard transductive node classification benchmarks, it can exceed or match the performance of state-of-the-art GNNs by combining shallow models that ignore the graph structure with two simple post-processing steps that exploit correlation in the label structure.
Decoupled Smoothing on Graphs
TLDR
This work presents a decoupled approach to graph smoothing that decouples notions of “identity” and “preference,” resulting in an alternative social phenomenon of monophily whereby individuals are similar to “the company they're kept in,’ as observed in recent empirical work.
Graph Convolutional Neural Networks for Web-Scale Recommender Systems
TLDR
A novel method based on highly efficient random walks to structure the convolutions and a novel training strategy that relies on harder-and-harder training examples to improve robustness and convergence of the model are developed.
...
1
2
3
4
5
...