Identity-aware Graph Neural Networks

@inproceedings{You2021IdentityawareGN,
  title={Identity-aware Graph Neural Networks},
  author={Jiaxuan You and Jonathan M. Gomes-Selman and Rex Ying and Jure Leskovec},
  booktitle={AAAI},
  year={2021}
}
Message passing Graph Neural Networks (GNNs) provide a powerful modeling framework for relational data. However, the expressive power of existing GNNs is upper-bounded by the 1-Weisfeiler-Lehman (1-WL) graph isomorphism test, which means GNNs that are not able to predict node clustering coefficients and shortest path distances, and cannot differentiate between different d-regular graphs. Here we develop a class of message passing GNNs, named Identity-aware Graph Neural Networks (ID-GNNs), with… 

Figures and Tables from this paper

Fea2Fea: Exploring Structural Feature Correlations via Graph Neural Networks

This paper introuduce graph feature to feature (Fea2Fea) prediction pipelines in a low dimensional space to explore some preliminary results on structural feature correlation, which is based on graph neural network and shows that there exists high correlation between some of the structural features.

A N EW P ERSPECTIVE ON "H OW G RAPH N EURAL N ET WORKS G O B EYOND W EISFEILER -L EHMAN ?"

This work proposes a novel neural model, called GraphSNN, and proves that this model is strictly more expressive than the Weisfeiler Lehman test in distinguishing graph structures, and empirically verify the strength of the model on different graph learning tasks.

A Survey on Graph Representation Learning Methods

An overview of non-GNN graph embedding methods, which are based on techniques such as random walks, temporal point processes and neural network learning methods, and GNN-based methods which are the application of deep learning on graph data are provided.

Equivariant Subgraph Aggregation Networks

A novel framework to represent each graph as a set of subgraphs derived by some predefined policy, and to process it using a suitable equivariant architecture, and it is proved that this approach increases the expressive power of both MPNNs and more expressive architectures.

Revisiting Graph Neural Networks for Link Prediction

It is concluded that simply aggregating node embeddings does not lead to effective link representations, while learning from properly labeled subgraphs around links provides highly expressive and generalizable link representations.

Graph Neural Networks for Link Prediction with Subgraph Sketching

Many Graph Neural Networks (GNNs) perform poorly compared to simple heuristics on Link Prediction (LP) tasks. This is due to limitations in expressive power such as the inability to count triangles

Understanding and Extending Subgraph GNNs by Rethinking Their Symmetries

The most prominent form of subgraph methods, which employs node-based subgraph selection policies such as ego-networks or node marking and deletion, is studied and a novel Subgraph GNN dubbed SUN is designed, which theoretically unifies previous architectures while providing better empirical performance on multiple benchmarks.

Data Augmentation for Deep Graph Learning: A Survey

A taxonomy for graph data augmentation techniques is proposed and a structured review by categorizing the related work based on the augmented information modalities is provided, which points out promising research directions and the challenges in future research.

Distance and Hop-wise Structures Encoding Enhanced Graph Attention Networks

This work first extracting hop-wise structure information and compute distance distributional information, gathering with node’s intrinsic features, embedding them into same vector space and then adding them up, showing that the DHSEGATs achieve competitive result.

Adjacency Matrix Node Features Laplacian Eigenvectors SignNet Prediction Model ( e . g . GNN , Transformer ) Compute Eigvecs Input Graph Model

  • 2022
...

References

SHOWING 1-10 OF 48 REFERENCES

Position-aware Graph Neural Networks

Position-aware Graph Neural Networks (P-GNNs) are proposed, a new class of GNNs for computing position-aware node embeddings that are inductive, scalable, and can incorporate node feature information.

How Powerful are Graph Neural Networks?

This work characterize the discriminative power of popular GNN variants, such as Graph Convolutional Networks and GraphSAGE, and show that they cannot learn to distinguish certain simple graph structures, and develops a simple architecture that is provably the most expressive among the class of GNNs.

Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks

It is shown that GNNs have the same expressiveness as the Weisfeiler-Leman graph isomorphism heuristic in terms of distinguishing non-isomorphic (sub-)graphs, and a generalization of GNN's is proposed, so-called $k$-dimensional GNNS ($k-GNNs), which can take higher-order graph structures at multiple scales into account.

GNNExplainer: Generating Explanations for Graph Neural Networks

GnExplainer is proposed, the first general, model-agnostic approach for providing interpretable explanations for predictions of any GNN-based model on any graph-based machine learning task.

Distance Encoding: Design Provably More Powerful Neural Networks for Graph Representation Learning

A general class of structure-related features, termed Distance Encoding (DE), that assists GNNs in representing any set of nodes, while providing strictly more expressive power than the 1-WL test and significantly outperform other state-of-the-art methods especially designed for the above tasks.

Improving Graph Neural Network Expressivity via Subgraph Isomorphism Counting

Graph Substructure Networks (GSN) is proposed, a topologically-aware message passing scheme based on substructure encoding that allows for multiple attractive properties of standard GNNs such as locality and linear network complexity, while being able to disambiguate even hard instances of graph isomorphism.

Relational Pooling for Graph Representations

This work generalizes graph neural networks (GNNs) beyond those based on the Weisfeiler-Lehman (WL) algorithm, graph Laplacians, and diffusions to provide a framework with maximal representation power for graphs.

Provably Powerful Graph Networks

This paper proposes a simple model that interleaves applications of standard Multilayer-Perceptron (MLP) applied to the feature dimension and matrix multiplication and shows that a reduced 2-order network containing just scaled identity operator, augmented with a single quadratic operation (matrix multiplication) has a provable 3-WL expressive power.

On the equivalence between graph isomorphism testing and function approximation with GNNs

It is proved that order-2 Graph G-invariant networks fail to distinguish non-isomorphic regular graphs with the same degree, and is extended to a new architecture, Ring-GNNs, which succeeds on distinguishing these graphs and provides improvements on real-world social network datasets.

Graph Neural Networks for Social Recommendation

This paper provides a principled approach to jointly capture interactions and opinions in the user-item graph and proposes the framework GraphRec, which coherently models two graphs and heterogeneous strengths for social recommendations.