DSKReG: Differentiable Sampling on Knowledge Graph for Recommendation with Relational GNN

Wang, Yu; Liu, Zhiwei; Fan, Ziwei; Sun, Lichao; Yu, Philip S.

doi:10.1145/3459637.3482092

Cited by 37 publications

(10 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the exponential increase of a node's receptive field places a severe constraint on high-order aggregation. Differentiable Sampling on Knowledge Graph for Recommendation with Relational GNN (DSKReG) [60] proposed learning the relevance distribution of related items from knowledge graphs and sampling relevant items in accordance with this distribution. With this model's addition of a differentiable sampling method, the selection of appropriate objects can be optimized as the model is being trained.…”

Section: Figure 5 Illustration Of User-item Interactions and The Know...mentioning

confidence: 99%

A Comprehensive Survey of Graph Neural Networks for Knowledge Graphs

Kumar

Sing

et al. 2022

IEEE Access

View full text Add to dashboard Cite

The Knowledge graph, a multi-relational graph that represents rich factual information among entities of diverse classifications, has gradually become one of the critical tools for knowledge management. However, the existing knowledge graph still has some problems which form hot research topics in recent years. Numerous methods have been proposed based on various representation techniques. Graph Neural Network, a framework that uses deep learning to process graph-structured data directly, has significantly advanced the state-of-the-art in the past few years. This study firstly is aimed at providing a broad, complete as well as comprehensive overview of GNN-based technologies for solving four different KG tasks, including link prediction, knowledge graph alignment, knowledge graph reasoning, and node classification. Further, we also investigated the related artificial intelligence applications of knowledge graphs based on advanced GNN methods, such as recommender systems, question answering, and drugdrug interaction. This review will provide new insights for further study of KG and GNN.

show abstract

Section: Figure 5 Illustration Of User-item Interactions and The Know...mentioning

confidence: 99%

A Comprehensive Survey of Graph Neural Networks for Knowledge Graphs

Kumar

Sing

et al. 2022

IEEE Access

View full text Add to dashboard Cite

show abstract

“…A larger indicator means the higher the ranking of the items that users are most interested in the Top K recommendation set. The formula of MRR@K is as follows in Equation (22).…”

Section: Evaluation Metrics Analysismentioning

confidence: 99%

“…Considering that not all the entities and relationships in the knowledge graph are related to the recommendation task, Reference 21 proposes Knowledge‐aware Conditional Attention Networks to refine the whole knowledge graph into specific subgraphs for the recommendation goal according to the recommendation goal. Considering that users have different preferences for interactive relationships in the knowledge graph, the Reference 22 proposes a method of differentiable sampling to assign weights to the relationships in the knowledge graph, so as to select neighbors with a high correlation with users for the recommendation. In order to reduce the difficulty of graph convolution network training and improve the recommendation effect, Xiang nan et al 23 propose the LightGCN model, which deleted the two operations of feature transformation and nonlinear activation on the basis of the GCN.…”

Section: Related Workmentioning

confidence: 99%

A multitask recommendation algorithm based on DeepFM and Graph Convolutional Network

Chen

Fan

et al. 2022

Concurrency and Computation

View full text Add to dashboard Cite

For a long time, the problems of cold start and sparse data have always been the key problems to be solved by the recommendation system. Researchers usually use auxiliary information to deal with the aforementioned problems, thereby achieving the purpose of enhancing the recommendation effect. For example, the multitask feature learning framework (MKR) uses knowledge graphs as auxiliary information to enhance recommendations. However, the MKR algorithm has the problem of insufficient semantic information representation which affect the recommendation results.

show abstract

“…Recommender systems [6,9,25,26,44] become crucial components in web applications [23], which provide personalized item lists by modeling interactions between users and items. Sequential recommendation (SR) attracts a lot of attention from both the academic community and industry due to its success and scalability.…”

Section: Introductionmentioning

confidence: 99%

Sequential Recommendation via Stochastic Self-Attention

Fan¹,

Liu²,

Wang³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Sequential recommendation models the dynamics of a user's previous behaviors in order to forecast the next item, and has drawn a lot of attention. Transformer-based approaches, which embed items as vectors and use dot-product self-attention to measure the relationship between items, demonstrate superior capabilities among existing sequential methods. However, users' real-world sequential behaviors are uncertain rather than deterministic, posing a significant challenge to present techniques. We further suggest that dot-product-based approaches cannot fully capture collaborative transitivity, which can be derived in item-item transitions inside sequences and is beneficial for cold start items. We further argue that BPR loss has no constraint on positive and sampled negative items, which misleads the optimization.We propose a novel STOchastic Self-Attention (STOSA) to overcome these issues. STOSA, in particular, embeds each item as a stochastic Gaussian distribution, the covariance of which encodes the uncertainty. We devise a novel Wasserstein Self-Attention module to characterize item-item position-wise relationships in sequences, which effectively incorporates uncertainty into model training. Wasserstein attentions also enlighten the collaborative transitivity learning as it satisfies triangle inequality. Moreover, we introduce a novel regularization term to the ranking loss, which assures the dissimilarity between positive and the negative items. Extensive experiments on five real-world benchmark datasets demonstrate the superiority of the proposed model over state-of-the-art baselines, especially on cold start items. The code is available in https://github.com/zfan20/STOSA.

show abstract

DSKReG: Differentiable Sampling on Knowledge Graph for Recommendation with Relational GNN

Cited by 37 publications

References 30 publications

A Comprehensive Survey of Graph Neural Networks for Knowledge Graphs

A Comprehensive Survey of Graph Neural Networks for Knowledge Graphs

A multitask recommendation algorithm based on DeepFM and Graph Convolutional Network

Sequential Recommendation via Stochastic Self-Attention

Contact Info

Product

Resources

About