Graph Attention Auto-Encoders

Salehi, Amin; Davulcu, Hasan

doi:10.1109/ictai50040.2020.00154

Cited by 75 publications

(49 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To better capture the relevance between nodes and neighbors, we employ attention mechanism [32]. To be precise, the relevance of a neighboring node j to node i in the s-th graph can defined as:…”

Section: B Self-reconstructionmentioning

confidence: 99%

Multilayer Graph Contrastive Clustering Network

Liu¹,

Zhao²,

Liu³

et al. 2021

Preprint

View full text Add to dashboard Cite

Multilayer graph has garnered plenty of research attention in many areas due to their high utility in modeling interdependent systems. However, clustering of multilayer graph, which aims at dividing the graph nodes into categories or communities, is still at a nascent stage. Existing methods are often limited to exploiting the multiview attributes or multiple networks and ignoring more complex and richer network frameworks. To this end, we propose a generic and effective autoencoder framework for multilayer graph clustering named Multilayer Graph Contrastive Clustering Network (MGCCN). MGCCN consists of three modules: (1)Attention mechanism is applied to better capture the relevance between nodes and neighbors for better node embeddings. (2)To better explore the consistent information in different networks, a contrastive fusion strategy is introduced. (3)MGCCN employs a self-supervised component that iteratively strengthens the node embedding and clustering. Extensive experiments on different types of real-world graph data indicate that our proposed method outperforms stateof-the-art techniques.

show abstract

Section: B Self-reconstructionmentioning

confidence: 99%

Multilayer Graph Contrastive Clustering Network

Liu¹,

Zhao²,

Liu³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Then STGATE learns low-dimensional latent embeddings with both spatial information and gene expressions via a graph attention auto-encoder [14] (Fig. 1).…”

Section: Overview Of Stgatementioning

confidence: 99%

Deciphering spatial domains from spatially resolved transcriptomics with adaptive graph attention auto-encoder

Dong

Zhang

2021

Preprint

View full text Add to dashboard Cite

Recent advances in spatially resolved transcriptomics have enabled comprehensive measurements of gene expression patterns while retaining spatial context of tissue microenvironment. Deciphering the spatial context of spots in a tissue needs to use their spatial information carefully. To this end, we developed a graph attention auto- encoder framework STGATE to accurately identify spatial domains by learning low-dimensional latent embeddings via integrating spatial information and gene expression profiles. To better characterize the spatial similarity at the boundary of spatial domains, STGATE adopts an attention mechanism to adaptively learn the similarity of neighboring spots, and an optional cell type-aware module through integrating the pre-clustering of gene expressions. We validated STGATE on diverse spatial transcriptomics datasets generated by different platforms with different spatial resolutions. STGATE could substantially improve the identification accuracy of spatial domains, and denoise the data while preserving spatial expression patterns. Importantly, STGATE could be extended to multiple consecutive sections for reducing batch effects between sections and extracting 3D expression domains from the reconstructed 3D tissue effectively.

show abstract

“…In this paper, we regard cold-start as a missing data problem where user-item interaction data is missing. Inspired by denoising auto-encoders [26] that train the model to reconstruct the input from a corrupted version, as well as the classical framework graph auto-encoders [4,20,31], we propose a novel model named Multi-view Denoising Graph Auto-Encoders (MvDGAE) on HINS to alleviate the cold-start problem. We first extract multifaceted meaningful semantics reflected by meta-path on HINs as multiviews for both users and items, effectively enhancing user/item relationships on different aspects.…”

Section: Introductionmentioning

confidence: 99%

Multi-view Denoising Graph Auto-Encoders on Heterogeneous Information Networks for Cold-start Recommendation

Zheng

et al. 2021

Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery &Amp; Data Mining

View full text Add to dashboard Cite

Cold-start recommendation is a challenging problem due to the lack of user-item interactions. Recently, heterogeneous information network (HIN)-based recommendation methods use rich auxiliary information to enhance users and items' connections, helping alleviate the cold-start problem. Despite progress, most existing methods model HINs under traditional supervised learning settings, ignoring the gaps between training and inference procedures in cold-start scenarios. In this paper, we regard cold-start recommendation as a missing data problem where some user-item interaction data are missing. Inspired by denoising auto-encoders that train a model to reconstruct the input from its corrupted version, we propose a novel model called Multi-view Denoising Graph Auto-Encoders (MvDGAE) on HINS. Specifically, we first extract multifaceted meaningful semantics on HINs as multi-views for both users and items, effectively enhancing user/item relationships on different aspects. Then we conduct the training procedure by randomly dropping out some user-item interactions in the encoder while forcing the decoder to use these limited views to recover the full views, including the missing ones. In this way, the complementary representations for both users and items are more informative and robust to adjust to cold-start scenarios. Moreover, the decoder's reconstruction goals are multi-view user-user and item-item relationship graphs rather than the original input graphs, which make the features of similar users (or items) in the meta-paths closer together. Finally, we adopt a Bayesian task weight learner to balance multi-view graph reconstruction objectives automatically. Extensive experiments on both public benchmark datasets and a large-scale industry dataset WeChat Channel demonstrate that MvDGAE significantly outperforms the state-of-the-art recommendation models in various cold-start scenarios. The case studies also illustrate that MvDGAE has potentially good interpretability. CCS CONCEPTS• Information systems → Data mining; Collaborative filtering.

show abstract

Graph Attention Auto-Encoders

Cited by 75 publications

References 24 publications

Multilayer Graph Contrastive Clustering Network

Multilayer Graph Contrastive Clustering Network

Deciphering spatial domains from spatially resolved transcriptomics with adaptive graph attention auto-encoder

Multi-view Denoising Graph Auto-Encoders on Heterogeneous Information Networks for Cold-start Recommendation

Contact Info

Product

Resources

About