Heterogeneous Edge Embedding for Friend Recommendation

Verma, Janu; Gupta, Srishti; Mukherjee, Debdoot; Chakraborty, Tanmoy

doi:10.1007/978-3-030-15719-7_22

Cited by 18 publications

(14 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Pointwise learning models transfer the sorting problem into a multi-classification problem or a regression problem [11], [12], and the disadvantage is that these models cannot deal with the high skewness of data very well. Pairwise learning models treat friend recommendation as a learning to rank problem based upon pairwise comparisons [14], [19], [24]- [26], [43]. Such kind of approaches can better overcome the problem of data skewness, but often suffers the problem of too large training dataset size and high time complexity.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

HeteroRWR: A Novel Algorithm for Top-<i>k</i> Co-Author Recommendation with Fusion of Citation Networks

Zhao

Peng

Zhang

et al. 2020

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

It is of great importance to recommend collaborators for scholars in academic social networks, which can benefit more scientific research results. Facing the problem of data sparsity of co-author recommendation in academic social networks, a novel recommendation algorithm named HeteroRWR (Heterogeneous Random Walk with Restart) is proposed. Different from the basic Random Walk with Restart (RWR) model which only walks in homogeneous networks, HeteroRWR implements multiple random walks in a heterogeneous network which integrates a citation network and a co-authorship network to mine the k mostly valuable coauthors for target users. By introducing the citation network, HeteroRWR algorithm can find more suitable candidate authors when the co-authorship network is extremely sparse. Candidate recommenders will not only have high topic similarities with target users, but also have good community centralities. Analyses on the convergence and time efficiency of the proposed approach are presented. Extensive experiments have been conducted on DBLP and CiteSeerX datasets. Experimental results demonstrate that Het-eroRWR outperforms state-of-the-art baseline methods in terms of precision and recall rate even in the case of incorporating an incomplete citation dataset.

show abstract

Section: Related Workmentioning

confidence: 99%

“…It can model different objects and their rich relations in RSs, in which objects are of different types and links among objects represent different relations. HINbased recommendation model can better overcome the data sparsity problem because of the ability to integrate abundant information into the model [19], [27]- [29].…”

Section: Related Workmentioning

confidence: 99%

HeteroRWR: A Novel Algorithm for Top-<i>k</i> Co-Author Recommendation with Fusion of Citation Networks

Zhao

Peng

Zhang

et al. 2020

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

show abstract

“…Most of the research work has been focused on the extraction of information from the network by making network specific assumptions. These traditional mechanisms perform well on the specific networks while they fail miserably on the networks in which the assumptions do not hold true [8]. There are techniques like node embedding that encode the nodes present in the network into low dimensional vectors.…”

Section: Related Workmentioning

confidence: 99%

“…There has been a lot of research in Link Prediction. Most of the work is focused on exploiting structural information using hand engineered features in which specific aspects and assumptions are taken into consideration [8]. Most of the work in link prediction revolves around exploiting the structure of the network in order to compute features based on various assumptions about the given network and predicting links based on those features.…”

Section: Introductionmentioning

confidence: 99%

Link Prediction in Complex Networks using Embedding Techniques and Similarity Measures

Kumar*,

Gupta,

Singh

2020

IJITEE

View full text Add to dashboard Cite

Networks have proved to be very helpful in modelling complex systems with interacting components. There are various problems across various domains where the systems can be modelled in the form of a network with links between interacting components. The Problem of Link Prediction deals with predicting missing links in a given network. The application of link prediction ranges across various disciplines including biological networks, transportation networks, social networks, telecommunication networks, etc. In this paper, we use node embedding methods to encode the nodes into low dimensional embeddings and predict links based on the edge embeddings computed by taking the hadamard product of the participating nodes. We further compare the accuracy of the models trained on different dimensions of embeddings. We also study how the introduction of additional features changes the accuracy when introduced to various dimensions of node embeddings. The additional features include overlapping measures such as Jaccard similarity, Adamic-Adar score and dot product between node embeddings as well as heuristic features i.e. Common Neighbors, Resource Allocation, preferential attachment and friend tns score.

show abstract

“…Figure 2, the initialization of shared node embedding could be random or pre-defined. Since the experiment results of [44] suggested that Node2Vec is more efficient than DeepWalk as the node initialization of their edge embedding model, we adopt Node2Vec as the pre-defined node initialization method and investigate if it's beneficial to MERL. Table 4 shows that the MERL variants with Node2Vec initialization outperform other variants without Node2Vec initialization.…”

Section: Conversation Factorsmentioning

confidence: 99%

Merl

Lai

Neville

2020

Proceedings of the 29th ACM International Conference on Information &Amp; Knowledge Management

View full text Add to dashboard Cite

Network embedding models aim to learn low-dimensional representations for nodes and/or edges in graphs. For social networks, learning edge representations is especially beneficial as we need to describe or explain the relationships, activities, and interactions between users. Existing approaches that learn stand-alone node embeddings, and represent edges as pairs of node embeddings, are limited in their applicability because nodes participate in multiple relationships, which should be considered. In addition, social networks often contain multiple types of edges, which yields multiview contexts that need to be considered in the representation. In this paper, we propose a new methodology, MERL, that (1) captures asymmetry in multiple views by learning well-defined edge representations that are responsive to the difference between the source and destination node roles, and (2) incorporates textual communications to identify multiple source of social signals (e.g. strength and affinity) that moderate the impact of different views between users. Our experiments show that MERL outperforms alternative state-of-the-art embedding models on link prediction and multilabel classification tasks across multiple views in social network datasets. We further analyze the learned embeddings of MERL and demonstrate they are more correlated with the existence of view-based edges compared to previous methods. CCS CONCEPTS • Information systems → Social networks; • Computing methodologies → Learning latent representations.

show abstract

Heterogeneous Edge Embedding for Friend Recommendation

Cited by 18 publications

References 16 publications

HeteroRWR: A Novel Algorithm for Top-<i>k</i> Co-Author Recommendation with Fusion of Citation Networks

HeteroRWR: A Novel Algorithm for Top-<i>k</i> Co-Author Recommendation with Fusion of Citation Networks

Link Prediction in Complex Networks using Embedding Techniques and Similarity Measures

Merl

Contact Info

Product

Resources

About