RECORD
GIPA: General Information Propagation Algorithm for Graph Learning
Machine Learning · Submitted 13 May 2021
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim The experimental results reveal that GIPA can beat the state-of-the-art models in terms of prediction accuracy, e.g., GIPA achieves an average test ROC-AUC of $0.8700\pm 0.0010$ and outperforms all the previous methods listed in the ogbn-proteins leaderboard.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
Graph neural networks (GNNs) have been popularly used in analyzing graph-structured data, showing promising results in various applications such as node classification, link prediction and network recommendation. In this paper, we present a new graph attention neural network, namely GIPA, for attributed graph data learning. GIPA consists of three key components: attention, feature propagation and aggregation. Specifically, the attention component introduces a new multi-layer perceptron based multi-head to generate better non-linear feature mapping and representation than conventional implementations such as dot-product. The propagation component considers not only node features but also edge features, which differs from existing GNNs that merely consider node features. The aggregation component uses a residual connection to generate the final embedding. We evaluate the performance of GIPA using the Open Graph Benchmark proteins (ogbn-proteins for short) dataset. The experimental results reveal that GIPA can beat the state-of-the-art models in terms of prediction accuracy, e.g., GIPA achieves an average test ROC-AUC of $0.8700\pm 0.0010$ and outperforms all the previous methods listed in the ogbn-proteins leaderboard.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | Graph neural networks (GNNs) have been popularly used in analyzing graph-structured data, showing promising results in various applications such as node classification, link prediction and network recommendation. | background 1.00 | 0.04 | 0.02 | asserted 0.98 |
| s1 | In this paper, we present a new graph attention neural network, namely GIPA, for attributed graph data learning. | contribution 1.00 | 0.86 | 0.04 | asserted 0.97 |
| s2 | GIPA consists of three key components: attention, feature propagation and aggregation. | method 0.91 | 0.65 | 0.03 | asserted 1.00 |
| s3 | Specifically, the attention component introduces a new multi-layer perceptron based multi-head to generate better non-linear feature mapping and representation than conventional implementations such as dot-product. | method 0.94 | 0.77 | 0.02 | asserted 0.99 |
| s4 | The propagation component considers not only node features but also edge features, which differs from existing GNNs that merely consider node features. | method 0.79 | 0.64 | 0.03 | asserted 1.00 |
| s5 | The aggregation component uses a residual connection to generate the final embedding. | method 0.99 | 0.78 | 0.03 | asserted 1.00 |
| s6 | We evaluate the performance of GIPA using the Open Graph Benchmark proteins (ogbn-proteins for short) dataset. | method 0.98 | 0.93 | 0.02 | asserted 0.97 |
| s7 | The experimental results reveal that GIPA can beat the state-of-the-art models in terms of prediction accuracy, e.g., GIPA achieves an average test ROC-AUC of $0.8700\pm 0.0010$ and outperforms all the previous methods listed in the ogbn-proteins leaderboard. | result 1.00 | 0.96 | 0.85 | asserted 1.00 |
What was examined, and what was not
- arXiv listing abstract v2
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
Graph neural networks (GNNs) have been popularly used in analyzing graph-structured data, showing promising results in various applications such as node classification, link prediction and network recommendation. In this paper, we present a new graph attention neural network, namely GIPA, for attributed graph data learning. GIPA consists of three key components: attention, feature propagation and aggregation. Specifically, the attention component introduces a new multi-layer perceptron based multi-head to generate better non-linear feature mapping and representation than conventional implementations such as dot-product. The propagation component considers not only node features but also edge features, which differs from existing GNNs that merely consider node features. The aggregation component uses a residual connection to generate the final embedding. We evaluate the performance of GIPA using the Open Graph Benchmark proteins (ogbn-proteins for short) dataset. The experimental results reveal that GIPA can beat the state-of-the-art models in terms of prediction accuracy, e.g., GIPA achieves an average test ROC-AUC of $0.8700\pm 0.0010$ and outperforms all the previous methods listed in the ogbn-proteins leaderboard.
Human review
References
How the literature uses it
1 arXiv paper cite this in 1 sentence
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.