Heterogeneous hypergraph embedding for document recommendation

Zhu, Yu; Guan, Ziyu; Tan, Shulong; Liu, Haifeng; Cai, Deng; He, Xiaofei

doi:10.1016/j.neucom.2016.07.030

Cited by 57 publications

(18 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, there are also a few approaches studying the hypergraph embedding problem, but they either focus on a n-uniform hypergraph (where all hyperedges contain a fixed number n of nodes) and thus capture only fixed-n-wise node proximity [2,31,44], or learn from hyperedges for heterogeneous event only (hyperedges linking nodes from different data domains) while ignoring edges within a data domain [14]. However, in this paper, as shown in Figure 1, our LBSN hypergraph contains both classical friendship edges (n=2) within the user domain and check-in hyperedges (n=4) across all four data domains.…”

Section: Graph Embeddingsmentioning

confidence: 99%

“…Even though a hypergraph can be transformed into a classical graph by breaking each hyperedge into multiple classical edges, such an irreversible process causes a certain information loss, leading to degraded performance of the learnt node embeddings on different tasks (see Section 5.2 and 5.3 for more detail). Second, there are also a few techniques studying the hypergraph embedding problem, but they either focus on a n-uniform hypergraph (where all hyperedges contain a fixed number n of nodes) and thus capture only fixed-n-wise node proximity [2,31,44], or learn from hyperedges for heterogeneous events only (hyperedges linking nodes from different data domains) while ignoring edges within a data domain [14]. However, as shown in Figure 1, the LBSN hypergraph typically contains both classical friendship edges (n=2) within the user domain and check-in hyperedges (n=4) across all four data domains.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Revisiting User Mobility and Social Relationships in LBSNs: A Hypergraph Embedding Approach

Yang

et al. 2019

The World Wide Web Conference

210

147

View full text Add to dashboard Cite

Location Based Social Networks (LBSNs) have been widely used as a primary data source to study the impact of mobility and social relationships on each other. Traditional approaches manually define features to characterize users' mobility homophily and social proximity, and show that mobility and social features can help friendship and location prediction tasks, respectively. However, these handcrafted features not only require tedious human efforts, but also are difficult to generalize. In this paper, by revisiting user mobility and social relationships based on a large-scale LBSN dataset collected over a long-term period, we propose LBSN2Vec, a hypergraph embedding approach designed specifically for LBSN data for automatic feature learning. Specifically, LBSN data intrinsically forms a hypergraph including both user-user edges (friendships) and user-time-POI-semantic hyperedges (check-ins). Based on this hypergraph, we first propose a random-walk-with-stay scheme to jointly sample user check-ins and social relationships, and then learn node embeddings from the sampled (hyper)edges by preserving n-wise node proximity (n = 2 or 4). Our evaluation results show that LBSN2Vec both consistently and significantly outperforms the state-of-the-art graph embedding methods on both friendship and location prediction tasks, with an average improvement of 32.95% and 25.32%, respectively. Moreover, using LBSN2Vec, we discover the asymmetric impact of mobility and social relationships on predicting each other, which can serve as guidelines for future research on friendship and location prediction in LBSNs.

show abstract

Section: Graph Embeddingsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Revisiting User Mobility and Social Relationships in LBSNs: A Hypergraph Embedding Approach

Yang

et al. 2019

The World Wide Web Conference

210

147

View full text Add to dashboard Cite

show abstract

“…Hyper2vec [13] introduce a flexible random walk model on hyper-networks in a semi-supervised setting. HHE [37] utilizes eigenvectors to find the optimal solution and learn the subspace representations, but the computational cost is a vital problem. HGE [33] designs an objective function for hyperedges to make involved node representations close to each other, but the model is not flexible for hyper-networks with different structures.…”

Section: Related Workmentioning

confidence: 99%

Hyper-Path-Based Representation Learning for Hyper-Networks

Huang

Liu

Song

2019

Proceedings of the 28th ACM International Conference on Information and Knowledge Management

View full text Add to dashboard Cite

Network representation learning has aroused widespread interests in recent years. While most of the existing methods deal with edges as pairwise relationships, only a few studies have been proposed for hyper-networks to capture more complicated tuplewise relationships among multiple nodes. A hyper-network is a network where each edge, called hyperedge, connects an arbitrary number of nodes. Different from conventional networks, hyper-networks have certain degrees of indecomposability such that the nodes in a subset of a hyperedge may not possess a strong relationship. That is the main reason why traditional algorithms fail in learning representations in hyper-networks by simply decomposing hyperedges into pairwise relationships. In this paper, we firstly define a metric to depict the degrees of indecomposability for hyper-networks. Then we propose a new concept called hyper-path and design hyperpath-based random walks to preserve the structural information of hyper-networks according to the analysis of the indecomposability. Then a carefully designed algorithm, Hyper-gram, utilizes these random walks to capture both pairwise relationships and tuplewise relationships in the whole hyper-networks. Finally, we conduct extensive experiments on several real-world datasets covering the tasks of link prediction and hyper-network reconstruction, and results demonstrate the rationality, validity, and effectiveness of our methods compared with those existing state-of-the-art models designed for conventional networks or hyper-networks.

show abstract

“…Li et al [36] learned the distributional word representation model by mixed word embeddings to explore semantic relations for users. By incorporating various relations among users, tags and resource, Zhu et al [37] proposed a novel heterogeneous hypergraph embedding framework for document recommendation. Based on user and item interaction graph, Dai et al [38] proposed a novel deep coevolutionary network model to capture complex mutual relationship between users and items, and their evolution.…”

Section: Similar Relationship Discoverymentioning

confidence: 99%

Group User Profile Modeling Based on Neural Word Embeddings in Social Networks

Zheng

Sangaiah

2018

Symmetry

View full text Add to dashboard Cite

How to find a user’s interest from similar users a fundamental research problems in socialized recommender systems. Despite significant advances, there exists diversity loss for the majority of recommender systems. With this paper, for expanding the user’s interest, we overcome this challenge by using representative and diverse similar users from followees. First, we model a personal user profile vector via word2vec and term frequency mechanisms. According to user profiles and their follow relationships, we compute content interaction similarity and follow interaction similarity. Second, by combining two kinds of interaction similarity, we calculate the social similarity and discover a diverse group with coverage and dissimilarity. The users in a diverse group can distinguish each other and cover the whole followees, which can model a group user profile (GUP). Then, by tracking the changes of followee set, we heuristically adjust the number of diverse group users and construct an adaptive GUP. Finally, we conduct experiments on Sina Weibo datasets for recommendation, and the experimental results demonstrate that the proposed GUP outperforms conventional approaches for diverse recommendation.

show abstract

Heterogeneous hypergraph embedding for document recommendation

Cited by 57 publications

References 43 publications

Revisiting User Mobility and Social Relationships in LBSNs: A Hypergraph Embedding Approach

Revisiting User Mobility and Social Relationships in LBSNs: A Hypergraph Embedding Approach

Hyper-Path-Based Representation Learning for Hyper-Networks

Group User Profile Modeling Based on Neural Word Embeddings in Social Networks

Contact Info

Product

Resources

About