22,810 Hits in 11.0 sec

Inductive Link Prediction for Nodes Having Only Attribute Information

Yu Hao, Xin Cao, Yixiang Fang, Xike Xie, Sibo Wang
2020 Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence  
Predicting the link between two nodes is a fundamental problem for graph data analytics. In attributed graphs, both the structure and attribute information can be utilized for link prediction.  ...  Most existing studies focus on transductive link prediction where both nodes are already in the graph.  ...  Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence  ... 
doi:10.24963/ijcai.2020/168 dblp:conf/ijcai/Hao0FX020 fatcat:hxtbipc62fccpm2rmhp34nexay

Learning graph representations of biochemical networks and its application to enzymatic link prediction [article]

Julie Jiang, Li-Ping Liu, Soha Hassoun
2020 arXiv   pre-print
Further, we show that graph embedding for predicting enzymatic links improves link prediction by 24% over fingerprint-similarity-based approaches.  ...  We explore both transductive (test nodes included in the training graph) and inductive (test nodes not part of the training graph) learning models.  ...  We show that link prediction using only graph connectivity is on par with using molecular similarity.  ... 
arXiv:2002.03410v1 fatcat:i7waobftvfevreenohggc5dvdm

Inductive Matrix Completion Using Graph Autoencoder [article]

Wei Shen, Chuheng Zhang, Yun Tian, Liang Zeng, Xiaonan He, Wanchun Dou, Xiaolong Xu
2021 arXiv   pre-print
to learn the node-specific representations based on these learnable embeddings and finally aggregates the representations of the target users and its corresponding item nodes to predict missing links.  ...  Recently, the graph neural network (GNN) has shown great power in matrix completion by formulating a rating matrix as a bipartite graph and then predicting the link between the corresponding user and item  ...  CONCLUSION In this paper, we propose Inductive Matrix Completion using Graph Autoencoder (IMC-GAE), which uses GAE to learn both graph patterns for inductive matrix completion and specific node representations  ... 
arXiv:2108.11124v1 fatcat:pzpgh7u3wza6dhezl5b2vrvkhi

Inductive Representation Learning in Temporal Networks via Causal Anonymous Walks [article]

Yanbang Wang, Yen-Yu Chang, Yunyu Liu, Jure Leskovec, Pan Li
2021 arXiv   pre-print
CAW-N is evaluated to predict links over 6 real temporal networks and uniformly outperforms previous SOTA methods by averaged 10% AUC gain in the inductive setting.  ...  Previous works in this area depend on either network node identities or rich edge attributes and typically fail to extract these laws.  ...  ACKNOWLEDGMENTS We thank Jiaxuan You and Rex Ying for their helpful discussion on the idea of Causal Anonymous Walks.  ... 
arXiv:2101.05974v4 fatcat:cw2vpjrqpzgc7exzkvtncduhau

Link Prediction with Contextualized Self-Supervision [article]

Daokun Zhang, Jie Yin, Philip S. Yu
2022 arXiv   pre-print
Link prediction aims to infer the link existence between pairs of nodes in networks/graphs.  ...  The CSSL framework can be trained in an end-to-end manner, with the learning of model parameters supervised by both the link prediction and self-supervised learning tasks.  ...  links, node attributes and their interactions; 2) the robustness against link sparsity and node attribute noise; 3) the inductive ability to accurately predict the links of out-of-sample nodes.  ... 
arXiv:2201.10069v2 fatcat:oyhu7cpoufbvtlrvw5coke5wye

Pay Attention to Relations: Multi-embeddings for Attributed Multiplex Networks [article]

Joshua Melton, Michael Ridenhour, Siddharth Krishnan
2022 arXiv   pre-print
Graph Convolutional Neural Networks (GCNs) have become effective machine learning algorithms for many downstream network mining tasks such as node classification, link prediction, and community detection  ...  Our model incorporates node attributes, motif-based features, relation-based GCN approaches, and relational self-attention to learn embeddings of nodes with respect to the various relations in a heterogeneous  ...  on both transductive and inductive link prediction tasks with four real-world datasets. 4) We propose to incorporate higher-order subgraph features as node attributes.  ... 
arXiv:2203.01903v1 fatcat:4jyfddcwnzarlotbqpkhxxvmu4

Inductive Learning on Commonsense Knowledge Graph Completion [article]

Bin Wang, Guangtao Wang, Jing Huang, Jiaxuan You, Jure Leskovec, C.-C. Jay Kuo
2021 arXiv   pre-print
Different from previous approaches, InductiveE ensures the inductive learning capability by directly computing entity embeddings from raw entity attributes/text.  ...  The graph encoder is a gated relational graph convolutional neural network that learns from a densified graph for more informative entity representation learning.  ...  Inductive learning on graphs Inductive learning is investigated in the last several years for both graphs and knowledge graphs.  ... 
arXiv:2009.09263v2 fatcat:fjwqsjcl7rdvnn262ptcr5poma

Inductive Graph Embeddings through Locality Encodings [article]

Nurudin Alvarez-Gonzalez, Andreas Kaltenbrunner, Vicenç Gómez
2020 arXiv   pre-print
Despite its simplicity, this method achieves state-of-the-art performance in tasks such as role detection, link prediction and node classification, and represents an inductive network embedding method  ...  Despite the overwhelming number of existing methods, is is unclear how to exploit network structure in a way that generalizes easily to unseen nodes, edges or graphs.  ...  Our results show that IGEL is scalable and can compete with transductive approaches in tasks such as link prediction on unattributed graphs.  ... 
arXiv:2009.12585v1 fatcat:wbpevwstpnd33l3yssdqgicjlu

A Survey on Temporal Graph Representation Learning and Generative Modeling [article]

Shubham Gupta, Srikanta Bedathur
2022 arXiv   pre-print
In this survey, we comprehensively review the neural time dependent graph representation learning and generative modeling approaches proposed in recent times for handling temporal graphs.  ...  They necessitate research beyond the work related to static graphs in terms of their generative modeling and representation learning.  ...  Attributes Attributes are a rich source of information, except for the structure of a graph.  ... 
arXiv:2208.12126v1 fatcat:ebuqxhdkdzcyfnpdounvsswhia

Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Ranking [article]

Aleksandar Bojchevski, Stephan Günnemann
2018 arXiv   pre-print
We propose Graph2Gauss - an approach that can efficiently learn versatile node embeddings on large scale (attributed) graphs that show strong performance on tasks such as link prediction and node classification  ...  Furthermore, we propose an unsupervised method that handles inductive learning scenarios and is applicable to different types of graphs: plain/attributed, directed/undirected.  ...  Table 1 : 1 Link prediction performance for real-world datasets with L = 128.  ... 
arXiv:1707.03815v4 fatcat:terkojmlkze4bm3hqbn65airjq

Machine learning techniques to make computers easier to use

Hiroshi Motoda, Kenichi Yoshida
1998 Artificial Intelligence  
A machine learning technique called graph-based induction (GM) efficiently extracts regularities from such data, based on which a user-adaptive interface is built that can predict the next command, generate  ...  We show that graph-based induction [25] can nicely be applied to the three learning tasks.  ...  Note that it is impractical to represent the graph structure by a single table of attribute-value pairs.  ... 
doi:10.1016/s0004-3702(98)00062-9 fatcat:3egioabdfjbvlpyjlmxazmdoce

Social networks and statistical relational learning: a survey

Floriana Esposito, Stefano Ferilli, Teresa M.A. Basile, Nicola Di Mauro
2012 International Journal of Social Network Mining  
With the spread of the internet, several complex interactions have taken place among people, giving rise to huge information networks based on these interactions.  ...  Statistical relational learning (SRL) is a very promising approach to SNM, since it combines expressive representation formalisms, able to model complex relational networks, with statistical methods able  ...  In Wang et al. (2005) , attributes on entities, link evidence and attributes on link evidence are exploited in a relational structure of the network to detect communities.  ... 
doi:10.1504/ijsnm.2012.051057 fatcat:6i7n2zrrj5geho3eh6nicay5nm

Hierarchical Message-Passing Graph Neural Networks [article]

Zhiqiang Zhong, Cheng-Te Li, Jun Pang
2022 arXiv   pre-print
classification, link prediction, and community detection.  ...  Graph Neural Networks (GNNs) have become a prominent approach to machine learning with graphs and have been increasingly applied in a multitude of domains.  ...  to capture interactions between far-away nodes, but it cannot be applied to inductive learning settings.  ... 
arXiv:2009.03717v2 fatcat:6upcxhe27rfzpgsrkdsb67alse

Subgraph Neighboring Relations Infomax for Inductive Link Prediction on Knowledge Graphs [article]

Xiaohan Xu, Peng Zhang, Yongquan He, Chengpeng Chao, Chaoyang Yan
2022 arXiv   pre-print
Inductive link prediction for knowledge graph aims at predicting missing links between unseen entities, those not shown in training stage.  ...  Experiments show that SNRI outperforms existing state-of-art methods by a large margin on inductive link prediction task, and verify the effectiveness of exploring complete neighboring relations in a global  ...  In order to predict links between brand-new entities, inductive link prediction task has been an active area of research, which requires model with the inductive ability for reasoning on graphs consisting  ... 
arXiv:2208.00850v3 fatcat:qev2s5w7dvalzc3k7qyfik5bdi

A Survey On Link Prediction With Or Without Time Aware Feature In Social Network

Prof. Khushboo Satpute*, Prof Pankaj Choudhary
2016 Zenodo  
In this Survey we summarized link prediction without temporal features and Link prediction with time aware features, particularly the relationship between the time stamps of interactions or links and how  ...  Many approach and method have been used for predicting a link in past years, a significant interest of the methods uses local and global structure of the graph to make predictions.  ...  He received the Masters of Technology in IT ,SOIT UIT RGTU.He has published my paper in Social network,Link predictions.  ... 
doi:10.5281/zenodo.50967 fatcat:hcmxyxlh5vhihg6v33gb3vb3cu
« Previous Showing results 1 — 15 out of 22,810 results