Semi-Supervised Graph-to-Graph Translation

Zhao, Tianxiang; Tang, Xianfeng; Zhang, Xiang; Wang, Suhang

doi:10.1145/3340531.3411977

Cited by 21 publications

(13 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Graph Neural Networks (GNNs) have shown their great power in modeling graph structured data for various applications [7,35,37,41,42]. To generalize neural networks for graphs, two categories of GNNs are proposed, i.e., spectral-based [1,17,22,23] and spatialbased [2,5,15,34].…”

Section: Related Work 21 Graph Neural Networkmentioning

confidence: 99%

Towards Robust Graph Neural Networks for Noisy Graphs with Sparse Labels

Dai

Jin

Liu

et al. 2022

Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining

Self Cite

View full text Add to dashboard Cite

Graph Neural Networks (GNNs) have shown their great ability in modeling graph structured data. However, real-world graphs usually contain structure noises and have limited labeled nodes. The performance of GNNs would drop significantly when trained on such graphs, which hinders the adoption of GNNs on many applications. Thus, it is important to develop noise-resistant GNNs with limited labeled nodes. However, the work on this is rather limited. Therefore, we study a novel problem of developing robust GNNs on noisy graphs with limited labeled nodes. Our analysis shows that both the noisy edges and limited labeled nodes could harm the message-passing mechanism of GNNs. To mitigate these issues, we propose a novel framework which adopts the noisy edges as supervision to learn a denoised and dense graph, which can downweight or eliminate noisy edges and facilitate message passing of GNNs to alleviate the issue of limited labeled nodes. The generated edges are further used to regularize the predictions of unlabeled nodes with label smoothness to better train GNNs. Experimental results on real-world datasets demonstrate the robustness of the proposed framework on noisy graphs with limited labeled nodes. CCS CONCEPTS• Computing methodologies → Semi-supervised learning settings; Neural networks.

show abstract

Section: Related Work 21 Graph Neural Networkmentioning

confidence: 99%

Towards Robust Graph Neural Networks for Noisy Graphs with Sparse Labels

Dai

Jin

Liu

et al. 2022

Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining

Self Cite

View full text Add to dashboard Cite

show abstract

“…Graph representation learning. Graph representation learning (GRL) aims to learn representations suitable for graph-based tasks, mainly including node/graph classification [21,48,50,62], and link prediction [17]. Early methods focused on non-attributed graphs, leveraging insights from language modeling [39] to learn embeddings which preserve node co-occurrence statistics on random walks [40].…”

Section: Related Workmentioning

confidence: 99%

Friend Story Ranking with Edge-Contextual Local Graph Convolutions

Tang

Liu

et al. 2022

Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining

Self Cite

View full text Add to dashboard Cite

Social platforms have paved the way in creating new, modern ways for users to communicate with each other. In recent years, multiple platforms have introduced "Stories" features, which enable broadcasting of ephemeral multimedia content. Specifically, "Friend Stories, " or Stories meant to be consumed by one's close friends, are a popular feature, promoting significant user-user interactions by allowing people to see (visually) what their friends and family are up to. A key challenge in surfacing Friend Stories for a given user, is in ranking over each viewing user's friends to efficiently prioritize and route limited user attention. In this work, we explore the novel problem of Friend Story Ranking from a graph representation learning perspective. More generally, our problem is a link ranking task, where inferences are made over existing links (relations), unlike common node or graph-based tasks, or link prediction tasks, where the goal is to make inferences about non-existing links. We propose ELR, an edge-contextual approach which carefully considers local graph structure, differences between local edge types and directionality, and rich edge attributes, building on the backbone of graph convolutions. ELR handles social sparsity challenges by considering and attending over neighboring nodes, and incorporating multiple edge types in local surrounding egonet structures. We validate ELR on two large country-level datasets with millions of users and tens of millions of links from Snapchat. ELR shows superior performance over alternatives by ≈ 8% and ≈ 5% error reduction measured by MSE and MAE correspondingly. Further generality, data efficiency and ablation experiments confirm the advantages of ELR.

show abstract

“…Graph Neural Networks (GNNs) have shown their great power in modeling graph-structure data for various applications such as traffic analysis [50] and drug generation [2]. GNNs can be generally split into two categories, i.e., spectral-based [3,18,20] and spatial-based [4,6,12,39,51].…”

Section: Related Work 21 Graph Neural Networkmentioning

confidence: 99%

Towards Self-Explainable Graph Neural Network

Dai

Wang

2021

Proceedings of the 30th ACM International Conference on Information &Amp; Knowledge Management

Self Cite

View full text Add to dashboard Cite

Graph Neural Networks (GNNs), which generalize the deep neural networks to graph-structured data, have achieved great success in modeling graphs. However, as an extension of deep learning for graphs, GNNs lack explainability, which largely limits their adoption in scenarios that demand the transparency of models. Though many efforts are taken to improve the explainability of deep learning, they mainly focus on i.i.d data, which cannot be directly applied to explain the predictions of GNNs because GNNs utilize both node features and graph topology to make predictions. There are only very few work on the explainability of GNNs and they focus on post-hoc explanations. Since post-hoc explanations are not directly obtained from the GNNs, they can be biased and misrepresent the true explanations. Therefore, in this paper, we study a novel problem of self-explainable GNNs which can simultaneously give predictions and explanations. We propose a new framework which can find 𝐾-nearest labeled nodes for each unlabeled node to give explainable node classification, where nearest labeled nodes are found by interpretable similarity module in terms of both node similarity and local structure similarity. Extensive experiments on real-world and synthetic datasets demonstrate the effectiveness of the proposed framework for explainable node classification. CCS CONCEPTS• Computing methodologies → Neural networks.

show abstract

Semi-Supervised Graph-to-Graph Translation

Cited by 21 publications

References 28 publications

Towards Robust Graph Neural Networks for Noisy Graphs with Sparse Labels

Towards Robust Graph Neural Networks for Noisy Graphs with Sparse Labels

Friend Story Ranking with Edge-Contextual Local Graph Convolutions

Towards Self-Explainable Graph Neural Network

Contact Info

Product

Resources

About