# EGC2: Enhanced Graph Classification with Easy Graph Compression

arXiv: https://arxiv.org/abs/2107.07737 · HTML: https://mlsanity.com/paper/2107.07737/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 51 references that are in the map.
- First posted on arXiv 16 Jul 2021.

## Builds on (most cited first, 24 of 24)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Open Graph Benchmark: Datasets for Machine Learning on Graphs](https://mlsanity.com/paper/2005.00687/) (2020)
- [Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering](https://mlsanity.com/paper/1606.09375/) (2016)
- [Hierarchical Graph Representation Learning with Differentiable Pooling](https://mlsanity.com/paper/1806.08804/) (2018)
- [Self-Attention Graph Pooling](https://mlsanity.com/paper/1904.08082/) (2019)
- [Adversarial Attack on Graph Structured Data](https://mlsanity.com/paper/1806.02371/) (2018)
- [graph2vec: Learning Distributed Representations of Graphs](https://mlsanity.com/paper/1707.05005/) (2017)
- [Backdoor Attacks to Graph Neural Networks](https://mlsanity.com/paper/2006.11165/) (2020)
- [AM-GCN: Adaptive Multi-channel Graph Convolutional Networks](https://mlsanity.com/paper/2007.02265/) (2020)
- [LGESQL: Line Graph Enhanced Text-to-SQL Model with Mixed Local and Non-Local Relations](https://mlsanity.com/paper/2106.01093/) (2021)
- [Graph Backdoor](https://mlsanity.com/paper/2006.11890/) (2020)
- [A Restricted Black-box Adversarial Framework Towards Attacking Graph Embedding Models](https://mlsanity.com/paper/1908.01297/) (2019)
- [Fast Gradient Attack on Network Embedding](https://mlsanity.com/paper/1809.02797/) (2018)
- [Graph Kernels: State-of-the-Art and Future Challenges](https://mlsanity.com/paper/2011.03854/) (2020)
- [Learning metrics for persistence-based summaries and applications for graph classification](https://mlsanity.com/paper/1904.12189/) (2019)
- [Explainability-based Backdoor Attacks Against Graph Neural Networks](https://mlsanity.com/paper/2104.03674/) (2021)
- [Universal Graph Transformer Self-Attention Networks](https://mlsanity.com/paper/1909.11855/) (2019)
- [Hybrid Approach of Relation Network and Localized Graph Convolutional Filtering for Breast Cancer Subtype Classification](https://mlsanity.com/paper/1711.05859/) (2017)
- [Robust Spammer Detection by Nash Reinforcement Learning](https://mlsanity.com/paper/2006.06069/) (2020)
- [Adversarial Attack on Hierarchical Graph Pooling Neural Networks](https://mlsanity.com/paper/2005.11560/) (2020)
- [Certified Robustness of Graph Classification against Topology Attack with Randomized Smoothing](https://mlsanity.com/paper/2009.05872/) (2020)
- [Blind Inference of Eigenvector Centrality Rankings](https://mlsanity.com/paper/2008.11330/) (2020)
- [Graph Convolutional Networks: analysis, improvements and results](https://mlsanity.com/paper/1912.09592/) (2019)

## Built on by (most cited first, 3 of 3)

- [Motif-Backdoor: Rethinking the Backdoor Attack on Graph Neural Networks via Motifs](https://mlsanity.com/paper/2210.13710/) (2022)
- [Local Structure-aware Graph Contrastive Representation Learning](https://mlsanity.com/paper/2308.03271/) (2023)
- [Multistage non-deterministic classification using secondary concept graphs and graph convolutional networks for high-level feature extraction](https://mlsanity.com/paper/2411.06212/) (2024)

## Abstract (arXiv)

Graph classification is crucial in network analyses. Networks face potential security threats, such as adversarial attacks. Some defense methods may trade off the algorithm complexity for robustness, such as adversarial training, whereas others may trade off clean example performance, such as smoothingbased defense. Most suffer from high complexity or low transferability. To address this problem, we proposed EGC2, an enhanced graph classification model with easy graph compression. EGC2 captures the relationship between the features of different nodes by constructing feature graphs and improving the aggregation of the node-level representations. To achieve lower-complexity defense applied to graph classification models, EGC2 utilizes a centrality-based edge-importance index to compress the graphs, filtering out trivial structures and adversarial perturbations in the input graphs, thus improving the model's robustness. Experiments on ten benchmark datasets demonstrate that the proposed feature read-out and graph compression mechanisms enhance the robustness of multiple basic models, resulting in a state-of-the-art performance in terms of accuracy and robustness against various adversarial attacks.