MODEL: Motif-Based Deep Feature Learning for Link Prediction

Wang, Lei; Ren, Jing; Xu, Bo; Li, Jianxin; Luo, Wei; Xia, Feng

doi:10.1109/tcss.2019.2962819

Cited by 44 publications

(22 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…) end for (12) end for (13) return f ALGORITHM 2: Feature representation. 8 Complexity lastly, we show how the different choices of these parameters affect the performance of link prediction.…”

Section: Methodsmentioning

confidence: 99%

“…e way to solve the link prediction problem [9][10][11][12][13][14] can be roughly divided into two categories, i.e., unsupervised methods and supervised methods. In current research work on unsupervised link prediction, they mainly focus on defining a similarity metric s uv for unconnected node pairs (u, v) using information extracted from the network topology.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Adaptive Similarity Function with Structural Features of Network Embedding for Missing Link Prediction

2021

View full text Add to dashboard Cite

Link prediction is a fundamental problem of data science, which usually calls for unfolding the mechanisms that govern the micro-dynamics of networks. In this regard, using features obtained from network embedding for predicting links has drawn widespread attention. Although methods based on edge features or node similarity have been proposed to solve the link prediction problem, many technical challenges still exist due to the unique structural properties of networks, especially when the networks are sparse. From the graph mining perspective, we first give empirical evidence of the inconsistency between heuristic and learned edge features. Then, we propose a novel link prediction framework, AdaSim, by introducing an Adaptive Similarity function using features obtained from network embedding based on random walks. The node feature representations are obtained by optimizing a graph-based objective function. Instead of generating edge features using binary operators, we perform link prediction solely leveraging the node features of the network. We define a flexible similarity function with one tunable parameter, which serves as a penalty of the original similarity measure. The optimal value is learned through supervised learning and thus is adaptive to data distribution. To evaluate the performance of our proposed algorithm, we conduct extensive experiments on eleven disparate networks of the real world. Experimental results show that AdaSim achieves better performance than state-of-the-art algorithms and is robust to different sparsities of the networks.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Adaptive Similarity Function with Structural Features of Network Embedding for Missing Link Prediction

2021

View full text Add to dashboard Cite

show abstract

“…Subgraphs embedding can be applied for learning molecular fingerprints [114] and predicting multicellular function [115], etc. In addition, the fixed-size subgraphs can be treated as motifs [116], [117] or graph kernel [118]. However, we will not discuss them but primarily focus on the deep learning-based NRL model.…”

Section: Subgraphs-based Modeling Methodsmentioning

confidence: 99%

Network Representation Learning: From Traditional Feature Learning to Deep Learning

Sun

Wang

et al. 2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

Network representation learning (NRL) is an effective graph analytics technique and promotes users to deeply understand the hidden characteristics of graph data. It has been successfully applied in many real-world tasks related to network science, such as social network data processing, biological information processing, and recommender systems. Deep Learning is a powerful tool to learn data features. However, it is non-trivial to generalize deep learning to graph-structured data since it is different from the regular data such as pictures having spatial information and sounds having temporal information. Recently, researchers proposed many deep learning-based methods in the area of NRL. In this survey, we investigate classical NRL from traditional feature learning method to the deep learning-based model, analyze relationships between them, and summarize the latest progress. Finally, we discuss open issues considering NRL and point out the future directions in this field.

show abstract

“…Another important matching is entity-relation matching in the knowledge graph representation. Recent years have witnessed a proliferation of knowledge graphs in many real-world applications such as semantic parsing [110], [111], information extraction [112], link prediction [113], [114], recommender systems [115], [116], question answering [117], [118] etc. Knowledge graph (KG) representation aims at transforming the symbolized components (e.g., entity and relation in a triplet) to vector, matrix, or tensor, which is easy to manipulate by computer.…”

Section: Entity-relation Matchingmentioning

confidence: 99%

Matching Algorithms: Fundamentals, Applications and Challenges

Ren

Xia

Chen

et al. 2021

IEEE Trans. Emerg. Top. Comput. Intell.

Self Cite

View full text Add to dashboard Cite

Matching plays a vital role in the rational allocation of resources in many areas, ranging from market operation to people's daily lives. In economics, the term matching theory is coined for pairing two agents in a specific market to reach a stable or optimal state. In computer science, all branches of matching problems have emerged, such as the questionanswer matching in information retrieval, user-item matching in a recommender system, and entity-relation matching in the knowledge graph. A preference list is the core element during a matching process, which can either be obtained directly from the agents or generated indirectly by prediction. Based on the preference list access, matching problems are divided into two categories, i.e., explicit matching and implicit matching. In this paper, we first introduce the matching theory's basic models and algorithms in explicit matching. The existing methods for coping with various matching problems in implicit matching are reviewed, such as retrieval matching, user-item matching, entity-relation matching, and image matching. Furthermore, we look into representative applications in these areas, including marriage and labor markets in explicit matching and several similarity-based matching problems in implicit matching. Finally, this survey paper concludes with a discussion of open issues and promising future directions in the field of matching.

show abstract

MODEL: Motif-Based Deep Feature Learning for Link Prediction

Cited by 44 publications

References 57 publications

Adaptive Similarity Function with Structural Features of Network Embedding for Missing Link Prediction

Adaptive Similarity Function with Structural Features of Network Embedding for Missing Link Prediction

Network Representation Learning: From Traditional Feature Learning to Deep Learning

Matching Algorithms: Fundamentals, Applications and Challenges

Contact Info

Product

Resources

About