Personalized entity recommendation: a heterogeneous information network approach

By Xiao Yu, Xiang Ren, Yizhou Sun, Quanquan Gu, Bradley Sturt, Urvashi Khandelwal, Brandon Norick, Jiawei Han. 2014

774 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Networks and Communications, Information Systems, Representation & Self-Supervised Learning, Graph Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Xiangnan He
2. Tat-seng Chua
3. Xiang Wang
4. Xing Xie
5. Philip S. Yu
6. Jure Leskovec
7. Chuan Shi
8. Hongwei Wang

In Computer Networks and Communications

1. Philip S. Yu
2. Chuan Shi
3. Xiangnan He
4. Steffen Rendle
5. Tat-seng Chua
6. Xiang Wang
7. Xing Xie
8. Xiao Wang

In Information Systems

1. Xiangnan He
2. Xiang Wang
3. Tat-seng Chua
4. Xing Xie
5. Meng Wang
6. Fuli Feng
7. Liqiang Nie
8. Yongfeng Zhang

In Representation & Self-Supervised Learning

1. Jure Leskovec
2. Peng Cui
3. Jian Tang
4. William L. Hamilton
5. Xiangnan He
6. Wenwu Zhu
7. Yizhou Sun
8. Philip S. Yu

In Graph Learning

1. Jure Leskovec
2. William L. Hamilton
3. Peng Cui
4. Jian Tang
5. Wenwu Zhu
6. Philip S. Yu
7. Yizhou Sun
8. Stephan Günnemann

Citations in the corpus

• LINE: Large-scale Information Network Embedding (2015, background): “Such a low-dimensional embedding is very useful in a variety of applications such as visualization [21], node classification [3], link prediction [10], and recommendation [23].”
• Knowledge Graph Convolutional Networks for Recommender Systems (2019, background): “For example, PER [22] and FMG [24] treat KG as a heterogeneous information network, and extract meta-path/meta-graph based latent features to represent the connectivity between users and items along different types of relation paths/graphs.”
• On the Effectiveness of Linear Models for One-Class Collaborative Filtering (2016, background): “We focus on approaches that rely only on information provided in R , and thus do not discuss approaches that exploit additional information, e.g. those that exploit an exogenous network amongst users or items (Yu et al. 2014; Sedhain et al. 2014).”
• RippleNet: Propagating User Preferences on the Knowledge Graph for Recommender Systems (2018, methodology): “uot; is of high relevance probability with "Forrest Gump" and "Robert Zemeckis" in the user’s 1-hop and 2-hop ripple set, respectively. Note that different from path-based methods [34, 36] where the patterns of path are manually designed, Ripple Network automatically discovers th”
• SHINE: Signed Heterogeneous Information Network Embedding for Sentiment Link Prediction (2017, background): “Additionally, several studies focus on representation learning in the scenario of heterogeneous network [3, 32], attributed network [10], or signed network [29, 33].”
• UniWalk: Explainable and Accurate Recommendation for Rating and Network Data (2017, background): “Another example shows that attributes of entities (e.g. genre) are used in recommending personalized entities [30].”
• GraphGAN: Graph Representation Learning with Generative Adversarial Nets (2017, background): “…applications such as link prediction (Gao, De-noyer, and Gallinari 2011), node classification (Tang, Ag-garwal, and Liu 2016), recommendation (Yu et al. 2014), visualization (Maaten and Hinton 2008), knowledge graph representation (Lin et al. 2015), clustering (Tian et al. 2014), text…”
• TEM: Tree-enhanced Embedding Model for Explainable Recommendation (2018, background): “Content-based works have considered various side information, ranging from item tags [38, 40], social relationships [31, 37], contextual reviews written by users [13, 15, 28, 31, 48] to knowledge graphs [3, 8, 47].”
• Meta-Graph Based Recommendation Fusion over Heterogeneous Information Networks (2017, methodology): “We set F and K to values in the range of [2, 3, 5, 10, 20, 30, 40, 50, 100].”
• A Survey on Accuracy-Oriented Neural Recommendation: From Collaborative Filtering to Information-Rich Recommendation (2021, background): “efforts for KG enhanced recommendation can be roughly categorized into three categories: path-basedmodels [168], [174], [175], [176], [177], regularization-based models [132], [169],”
• Collaborative Knowledge Base Embedding for Recommender Systems (2016, background): “For example, Yu et al. [30] uses a heterogeneous information network to represent users, items, item attributes, and the interlinked relationships in a knowledge base.”
• ClusCite: effective citation recommendation by information network-based clustering (2014, background): “[28] study personalized entity recommendation, which shares the similar idea of building local retrieval model for each cluster specifically.”
• Knowledge Graph Embedding: A Survey of Approaches and Applications (2017, background): “user-item interactions and auxiliary information of users or items, can usually achieve better performance [132].”
• Heterogeneous Information Network Embedding for Recommendation (2017, background): “HIN based recommendation has received much attention in the literature [7], [8], [9], [10], [11], [12].”
• entity2rec: Learning User-Item Relatedness from Knowledge Graphs for Top-N Item Recommendation (2017, background): “In [5, 28] the authors start from a graph-based data model encom-”
• Multi-Task Feature Learning for Knowledge Graph Enhanced Recommendation (2019, methodology): “mpareourproposedMKRwiththefollowingbaselines.Unless otherwise specified, the hyper-parameter settings of baselines are the same as reported in their original papers or as default in their codes. •PER [39] treats the KG as heterogeneous information networks and extracts meta-path based features to re”