• Corpus ID: 240354288

Higher-Order Relations Skew Link Prediction in Graphs

  title={Higher-Order Relations Skew Link Prediction in Graphs},
  author={Govind Sharma and Aditya Challa and Paarth Gupta and M. Narasimha Murty},
The problem of link prediction is of active interest. The main approach to solving the link prediction problem is based on heuristics such as Common Neighbors (CN) – more number of common neighbors of a pair of nodes implies a higher chance of them getting linked. In this article, we investigate this problem in the presence of higher-order relations. Surprisingly, it is found that CN works very well, and even better in the presence of higher-order relations. However, as we prove in the current… 

Figures and Tables from this paper

Higher-order Clustering and Pooling for Graph Neural Networks

This work proposes HoscPool, a clustering-based graph pooling operator that captures higher-order information hierarchically, leading to richer graph representations and provides a deep empirical analysis of pooling operators' inner functioning.

Dynamics on higher-order networks: a review

A variety of dynamical processes that have thus far been studied, including different synchronization phenomena, contagion processes, the evolution of cooperation and consensus formation, are studied.



Theoretical Justification of Popular Link Prediction Heuristics

A sequence of formal results are presented that show bounds related to the role that a node's degree plays in its usefulness for link prediction, the relative importance of short paths versus long paths, and the effects of increasing non-determinism in the link generation process on link prediction quality.

Predicting missing links via local information

A new similarity measure, motivated by the resource allocation process taking place on networks, is proposed and shown to have higher prediction accuracy than common neighbours, which can remarkably enhance the prediction accuracy.

An Axiomatic Approach to Link Prediction

This framework fully characterize four well known link prediction functions and shows that they are in fact derived from different variants of a single basic set of property templates, which are drawn upon in characterizations of ranking algorithms and other celebrated results from social choice.

A Survey of Link Prediction in Complex Networks

This survey will review the general-purpose techniques at the heart of the link prediction problem, which can be complemented by domain-specific heuristic methods in practice.

Link prediction in social networks: the state-of-the-art

A systematical category for link prediction techniques and problems is presented, and some future challenges of the link prediction in social networks are discussed.

Simplicial closure and higher-order link prediction

It is shown that there is a rich variety of structure in the authors' datasets but datasets from the same system types have consistent patterns of higher-order structure, and it is found that tie strength and edge density are competing positive indicators ofhigher-order organization.

The link-prediction problem for social networks

Experiments on large coauthorship networks suggest that information about future interactions can be extracted from network topology alone, and that fairly subtle measures for detecting node proximity can outperform more direct measures.

Higher order learning with graphs

It is shown that various formulations of the semi-supervised and the unsupervised learning problem on hypergraphs result in the same graph theoretic problem and can be analyzed using existing tools.

SimRank: a measure of structural-context similarity

A complementary approach, applicable in any domain with object-to-object relationships, that measures similarity of the structural context in which objects occur, based on their relationships with other objects is proposed.

Latent Space Modelling of Hypergraph Data

A model for hypergraph data is presented which extends the latent space distance model of Hoff et al. (2002) and, by drawing a connection to constructs from computational topology, is developed a model whose likelihood is inexpensive to compute.