Unifying Task-Oriented Knowledge Graph Learning and Recommendation

Li, Qianyu; Tang, Xiaoli; Wang, Tengyun; Yang, Haizhi; Song, Hengjie

doi:10.1109/access.2019.2932466

Cited by 24 publications

(15 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Translational models are widely used for training knowledge graph embeddings. Representative works includes attention-enhanced knowledge-aware user preference model (AKUPM) [12] and knowledge graph attention network (KGAT) [28]. They process each triple independently without considering multi-modal information fusion.…”

Section: Kg-based Recommendationmentioning

confidence: 99%

Multi-modal Knowledge Graphs for Recommender Systems

Sun

Cao²,

Zhao

et al. 2020

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

169

View full text Add to dashboard Cite

Recommender systems have shown great potential to solve the information explosion problem and enhance user experience in various online applications. To tackle data sparsity and cold start problems in recommender systems, researchers propose knowledge graphs (KGs) based recommendations by leveraging valuable external knowledge as auxiliary information. However, most of these works ignore the variety of data types (e.g., texts and images) in multi-modal knowledge graphs (MMKGs). In this paper, we propose Multi-modal Knowledge Graph Attention Network (MKGAT) to better enhance recommender systems by leveraging multi-modal knowledge. Specifically, we propose a multi-modal graph attention technique to conduct information propagation over MMKGs, and then use the resulting aggregated embedding representation for recommendation. To the best of our knowledge, this is the first work that incorporates multi-modal knowledge graph into recommender systems. We conduct extensive experiments on two real datasets from different domains, results of which demonstrate that our model MKGAT can successfully employ MMKGs to improve the quality of recommendation system.

show abstract

Section: Kg-based Recommendationmentioning

confidence: 99%

Multi-modal Knowledge Graphs for Recommender Systems

Sun

Cao²,

Zhao

et al. 2020

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

169

View full text Add to dashboard Cite

show abstract

“…In recent years, knowledge graph has gradually become a hot spot in academic research, especially in the field of recommendation algorithms [21]. Many researchers applied knowledge graph to recommend APIs for mashups [14], which has a good effect in solving the problem of sparsity.…”

Section: B Knowledge Graphmentioning

confidence: 99%

A Service Recommendation Algorithm Based on Knowledge Graph and Collaborative Filtering

Yang

Qin

et al. 2021

IEEE Access

View full text Add to dashboard Cite

With the rapid development of the Internet, the number of Web APIs is increasing. How to recommend accurate and appropriate Web APIs to mashups has become a focus and difficulty in the field of service computing. The existing methods are mainly based on collaborative filtering technology, but these methods have problems such as the data sparsity and cold start, which leads to poor recommendation effects. This paper proposes a service recommendation model based on knowledge graph and collaborative filtering. In this model, the knowledge graph connects the APIs and mashups related information to mine the potential relations between mashups and APIs, hence reducing the impact of data sparsity. All the API entities in the service knowledge graph are embedded into the low-dimensional space through the representation learning algorithm, then the distances between the API vectors are calculated to recommend the related APIs. In addition, in order to solve the cold-start problem of recommending APIs to target mashups that have no APIs usage, the similarities of functional sets extracted from mashups are calculated to recommend APIs for target mashups. At the same time, the model obtains the Mashup-API usage record, using the technology of collaborative filtering to recommend appropriate APIs to target mashups. Finally, the similarities of the above recommended APIs are normalized and sorted to form the final recommendation result. The experimental results show that our proposed model significantly improves the accuracy of service recommendation.

show abstract

“…Therefore, the many-to-one problem caused by time factor in DKGs mentioned above is easily handled. Inspired by the previous method [50], we learn the embeddings in Eq. 4, Eq.…”

Section: A Encoding Temporal Informationmentioning

confidence: 99%

“…Following the previous method [50], a parameter α is added for L tre (s − k,r ) in Eq. 7 to avoid excessive use of negative triples about relations, which may affect the ability of the model to differentiate entities.…”

Section: A Encoding Temporal Informationmentioning

confidence: 99%

Timespan-Aware Dynamic Knowledge Graph Embedding by Incorporating Temporal Evolution

Tang

Yuan

et al. 2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

Recently, Knowledge Graph Embedding (KGE) has attracted considerable research efforts, since it simplifies the manipulation while preserving the inherent structure of the KG. However to some extent, most existing KGE approaches ignore the historical changes of structural information involved in dynamic knowledge graphs (DKGs). To deal with this problem, this paper presents a Timespan-aware Dynamic knowledge Graph Embedding Evolution (TDG2E) method that considers temporal evolving process of DKGs. The major innovations of our paper are twofold. Firstly, a Gated Recurrent Units (GRU) based model is utilized in TDG2E to deal with the dependency among sub-KGs that is inevitably involved in the learning process of the dynamic knowledge graph embedding. Furthermore, we incorporate an auxiliary loss to supervise the learning process of the next sub-KG by utilizing previous structural information (i.e., the hidden state of GRU). In contrast with existing approaches in the literature (e.g., HyTE and t-TransE), TDG2E preserves structural information of current sub-KG and the temporal evolving process of the DKG simultaneously. Secondly, to further deal with the time unbalance issue underlying the DKGs, a Timespan Gate is designed in GRU. It makes TDG2E possible to model the temporal evolving process of DKGs more effectively by incorporating the timespan between adjacent sub-KGs. Extensive experiments on two large temporal datasets (i.e., YAGO11k and Wikidata12k) extracted from real-world KGs validate that the proposed TDG2E significantly outperforms traditional KGE methods in terms of Mean Rank and Hit Rate. INDEX TERMS Knowledge graph embedding, gated recurrent units, time unbalance.

show abstract

Unifying Task-Oriented Knowledge Graph Learning and Recommendation

Cited by 24 publications

References 30 publications

Multi-modal Knowledge Graphs for Recommender Systems

Multi-modal Knowledge Graphs for Recommender Systems

A Service Recommendation Algorithm Based on Knowledge Graph and Collaborative Filtering

Timespan-Aware Dynamic Knowledge Graph Embedding by Incorporating Temporal Evolution

Contact Info

Product

Resources

About