Learning Deep Network Representations with Adversarially Regularized Autoencoders

Yu, Wenchao; Zheng, Cheng; Cheng, Wei; Aggarwal, Charų C.; Song, Dongjin; Zong, Bo; Chen, Haifeng; Wang, Wei

doi:10.1145/3219819.3220000

Cited by 162 publications

(100 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This indicates the effectiveness of adversarial learning, i.e., dynamically playing a mini-max game either implicitly (GraphVAT) and explicitly (GraphSGAN) in the training phase. Moreover, the results are consistent with findings in previous work [15], [35], [42], [49]. • Among the baselines, 1) the methods that jointly account for the graph structure and node features (in the category of +Node Features) outperform LP and DeepWalk that only consider graph structure.…”

Section: Model Comparisonsupporting

confidence: 88%

Graph Adversarial Training: Dynamically Regularizing Based on Graph Structure

Feng

Tang

et al. 2021

IEEE Trans. Knowl. Data Eng.

131

View full text Add to dashboard Cite

Recent efforts show that neural networks are vulnerable to small but intentional perturbations on input features in visual classification tasks. Due to the additional consideration of connections between examples (e.g., articles with citation link tend to be in the same class), graph neural networks could be more sensitive to the perturbations, since the perturbations from connected examples exacerbate the impact on a target example. Adversarial Training (AT), a dynamic regularization technique, can resist the worst-case perturbations on input features and is a promising choice to improve model robustness and generalization. However, existing AT methods focus on standard classification, being less effective when training models on graph since it does not model the impact from connected examples. In this work, we explore adversarial training on graph, aiming to improve the robustness and generalization of models learned on graph. We propose Graph Adversarial Training (GraphAT), which takes the impact from connected examples into account when learning to construct and resist perturbations. We give a general formulation of GraphAT, which can be seen as a dynamic regularization scheme based on the graph structure. To demonstrate the utility of GraphAT, we employ it on a state-of-the-art graph neural network model -Graph Convolutional Network (GCN). We conduct experiments on two citation graphs (Citeseer and Cora) and a knowledge graph (NELL), verifying the effectiveness of GraphAT which outperforms normal training on GCN by 4.51% in node classification accuracy. Codes are available via: https://github.com/fulifeng/GraphAT.

show abstract

Section: Model Comparisonsupporting

confidence: 88%

Graph Adversarial Training: Dynamically Regularizing Based on Graph Structure

Feng

Tang

et al. 2021

IEEE Trans. Knowl. Data Eng.

131

View full text Add to dashboard Cite

show abstract

“…It avoids the problem that the LSTM network is not invariant to the permutation of node sequences. Network Representations with Adversarially Regularized Autoencoders (NetRA) [64] proposes a graph encoder-decoder framework with a general loss function, defined as L = −E z∼P data (z) (dist(z, dec(enc(z)))),…”

Section: A Network Embeddingmentioning

confidence: 99%

“…Graph-to-sequence learning learns to generate sentences with the same meaning given a semantic graph of abstract [22], [23], [25], [41], [43], [44], [45] [49], [50], [51], [53], [56], [61], [62] Citeseer [117] 1 3327 4732 3703 6 [22], [41], [43], [45], [50], [51], [53] [56], [61], [62] Pubmed [117] 1 19717 44338 500 3 [18], [22], [25], [41], [43], [44], [45] [49], [51], [53], [55], [56], [61], [62] [70], [95] DBLP (v11) [118] 1 4107340 36624464 -- [64], [70], [99] Biochemical Graphs PPI [119] 24 56944 818716 50 121 [18], [42], [43], [48], [45], [50]...…”

Section: Practical Applicationsmentioning

confidence: 99%

A Comprehensive Survey on Graph Neural Networks

Pan

Chen

et al. 2021

IEEE Trans. Neural Netw. Learning Syst.

6,220

2,977

View full text Add to dashboard Cite

Deep learning has revolutionized many machine learning tasks in recent years, ranging from image classification and video processing to speech recognition and natural language understanding. The data in these tasks are typically represented in the Euclidean space. However, there is an increasing number of applications where data are generated from non-Euclidean domains and are represented as graphs with complex relationships and interdependency between objects. The complexity of graph data has imposed significant challenges on existing machine learning algorithms. Recently, many studies on extending deep learning approaches for graph data have emerged. In this survey, we provide a comprehensive overview of graph neural networks (GNNs) in data mining and machine learning fields. We propose a new taxonomy to divide the state-of-the-art graph neural networks into four categories, namely recurrent graph neural networks, convolutional graph neural networks, graph autoencoders, and spatial-temporal graph neural networks. We further discuss the applications of graph neural networks across various domains and summarize the open source codes, benchmark data sets, and model evaluation of graph neural networks. Finally, we propose potential research directions in this rapidly growing field.

show abstract

“…This work was later expanded upon by Micheli [12] and Scarselli et al [13] In 2013, the Graph Convolutional Network (GCN) was presented by Bruna et al [14] using the principles of spectral graph theory. Many other forms of GNN have been presented since then, including, but not limited to, Graph Attention Networks [15], Graph Autoencoders [16][17][18][19], and Graph Spatial-Temporal Networks [20][21][22][23].…”

Section: Introductionmentioning

confidence: 99%

Building attention and edge message passing neural networks for bioactivity and physical–chemical property prediction

et al. 2020

View full text Add to dashboard Cite

Neural Message Passing for graphs is a promising and relatively recent approach for applying Machine Learning to networked data. As molecules can be described intrinsically as a molecular graph, it makes sense to apply these techniques to improve molecular property prediction in the field of cheminformatics. We introduce Attention and Edge Memory schemes to the existing message passing neural network framework, and benchmark our approaches against eight different physical-chemical and bioactivity datasets from the literature. We remove the need to introduce a priori knowledge of the task and chemical descriptor calculation by using only fundamental graph-derived properties. Our results consistently perform on-par with other state-of-the-art machine learning approaches, and set a new standard on sparse multi-task virtual screening targets. We also investigate model performance as a function of dataset preprocessing, and make some suggestions regarding hyperparameter selection.

show abstract

Learning Deep Network Representations with Adversarially Regularized Autoencoders

Cited by 162 publications

References 21 publications

Graph Adversarial Training: Dynamically Regularizing Based on Graph Structure

Graph Adversarial Training: Dynamically Regularizing Based on Graph Structure

A Comprehensive Survey on Graph Neural Networks

Building attention and edge message passing neural networks for bioactivity and physical–chemical property prediction

Contact Info

Product

Resources

About