paper-with-me

홈 › Papers

Learning From Graph Neighborhoods Using LSTMs

2016-11-21 · Rakshit Agrawal, Luca de Alfaro, Vassilis Polychronopoulos

Many prediction problems can be phrased as inferences over local neighborhoods of graphs. The graph represents the interaction between entities, and the neighborhood of each entity contains information that allows the inferences or predictions. We present an approach for applying machine learning directly to such graph neighborhoods, yielding predicitons for graph nodes on the basis of the structure of their local neighborhood and the features of the nodes in it. Our approach allows predictions to be learned directly from examples, bypassing the step of creating and tuning an inference model or summarizing the neighborhoods via a fixed set of hand-crafted features. The approach is based on a multi-level architecture built from Long Short-Term Memory neural nets (LSTMs); the LSTMs learn how to summarize the neighborhood from data. We demonstrate the effectiveness of the proposed technique on a synthetic example and on real-world data related to crowdsourced grading, Bitcoin transactions, and Wikipedia edit reversions.

📄 PDF Abstract BibTeX arXiv:1611.06882

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Mining Large Quasi-cliques with Quality Guarantees from Vertex Neighborhoods

2020-08-18 · Aritra Konar, Nicholas D. Sidiropoulos

Mining dense subgraphs is an important primitive across a spectrum of graph-mining tasks. In this work, we formally establish that two recurring characteristics of real-world graphs, namely heavy-tailed degree distributi…

ClusteringGraph Mining

Tree Decomposed Graph Neural Network

2021-08-25 · Yu Wang, Tyler Derr

Graph Neural Networks (GNNs) have achieved significant success in learning better representations by performing feature propagation and transformation iteratively to leverage neighborhood information. Nevertheless, itera…

Graph Neural NetworkNode ClassificationTree Decomposition

KONG: Kernels for ordered-neighborhood graphs

2018-05-25 · NeurIPS 2018 12 · Moez Draief, Konstantin Kutzkov, Kevin Scaman, Milan Vojnovic

We present novel graph kernels for graphs with node and edge labels that have ordered neighborhoods, i.e. when neighbor nodes follow an order. Graphs with ordered neighborhoods are a natural data representation for evolv…

Tree Communication Models for Sentiment Analysis

2019-07-01 · ACL 2019 7 · Yuan Zhang, Yue Zhang

Tree-LSTMs have been used for tree-based sentiment analysis over Stanford Sentiment Treebank, which allows the sentiment signals over hierarchical phrase structures to be calculated simultaneously. However, traditional t…

Sentiment Analysis

Neo-GNNs: Neighborhood Overlap-aware Graph Neural Networks for Link Prediction

2022-06-09 · NeurIPS 2021 12 · Seongjun Yun, Seoyoon Kim, Junhyun Lee, Jaewoo Kang 외

Graph Neural Networks (GNNs) have been widely applied to various fields for learning over graph-structured data. They have shown significant improvements over traditional heuristic methods in various tasks such as node c…

Graph ClassificationLink PredictionNode ClassificationPrediction