Knowledge-Enhanced Graph Neural Networks for Sequential Recommendation

Wang, Baocheng; Cai, Wentao

doi:10.3390/info11080388

Cited by 23 publications

(13 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This includes a variety of attribute representations aggregation methods [2,13,19,20] (e.g., average, sum, element-wise multiplication, etc. ), concatenation [3,13,31], parallel processing [9,16], usage of attention-based Transformer layer [30] and graph-based representations [27]. Furthermore, attributes have been utilized for introducing additional mask-based pre-training tasks [32] (e.g., predict an item's attribute).…”

Section: Related Workmentioning

confidence: 99%

Sequential Modeling with Multiple Attributes for Watchlist Recommendation in E-Commerce

Singer¹,

Roitman²,

Eshel³

et al. 2022

Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining

View full text Add to dashboard Cite

In e-commerce, the watchlist enables users to track items over time and has emerged as a primary feature, playing an important role in users' shopping journey. Watchlist items typically have multiple attributes whose values may change over time (e.g., price, quantity). Since many users accumulate dozens of items on their watchlist, and since shopping intents change over time, recommending the top watchlist items in a given context can be valuable. In this work, we study the watchlist functionality in e-commerce and introduce a novel watchlist recommendation task. Our goal is to prioritize which watchlist items the user should pay attention to next by predicting the next items the user will click. We cast this task as a specialized sequential recommendation task and discuss its characteristics. Our proposed recommendation model, Trans2D, is built on top of the Transformer architecture, where we further suggest a novel extended attention mechanism (Attention2D) that allows to learn complex item-item, attribute-attribute and item-attribute patterns from sequential-data with multiple item attributes. Using a large-scale watchlist dataset from eBay, we evaluate our proposed model, where we demonstrate its superiority compared to multiple state-of-the-art baselines, many of which are adapted for this task. CCS CONCEPTS• Applied computing → Electronic commerce.

show abstract

Section: Related Workmentioning

confidence: 99%

Sequential Modeling with Multiple Attributes for Watchlist Recommendation in E-Commerce

Singer¹,

Roitman²,

Eshel³

et al. 2022

Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining

View full text Add to dashboard Cite

show abstract

“…Graph GNN Sequential Modeling SURGE [14] item-item graph GAT RNN [145] item-item graph GCN Attention ISSR [91] item-item and user-item graph GCN RNN MA-GNN [100] item-item graph GCN Memory network DGSR [199] user-item graph GAT RNN GES-SASRec [215] item-item graph GCN RNN RetaGNN [59] temporal heterogeneous graph GAT Self Attention TGSRec [36] temporal user-item graph GAT GAT SGRec [85] item-item graph GAT GAT GME [179] item-item and user-item graph GAT GAT STP-UDGAT [90] item-item and user-item graph GAT GAT GPR [12] item-item and user-item graph GCN GCN learning long-term user interests through other networks. The learned multiple representations are fused together and used for final recommendation.…”

Section: Modelmentioning

confidence: 99%

“…Since GNN has the ability of high-order relationship modeling by aggregating information from neighbor nodes, after fusing multiple sequences into one graph, it can learn representations of both users and items in different sequences, which can't be accomplished by Markov model or recurrent neural network. Wang et al [145] propose a simple method that directly converts the sequence information into directed edges on the graph and then uses GNN to learn representations. Liu et al [91] construct a user-item bipartite graph and an item-item graph at the same time, where the edges of the item-item graph indicate co-occurrence in a sequence, with edge weights assigned according to the number of occurrences.…”

Section: Modelmentioning

confidence: 99%

“…Moreover, knowledge graph also offers a novel solution to some scenarios in recommendations, e.g., sequential recommendation [65,155], and objectives, e.g., explainability [152,185]. Currently, the majority of research first uses GNN to learn embeddings of knowledge graphs and then incorporate these embeddings into the recommendation model, so that an end-to-end model can be trained [145]. Therefore, we point out the utilization of KG in recommendation with GNN can be further enhanced from perspectives of data, scenario, and model.…”

Section: Kg-enhanced Recommendation With Gnnmentioning

confidence: 99%

See 1 more Smart Citation

A Survey of Graph Neural Networks for Recommender Systems: Challenges, Methods, and Directions

Chen¹,

Zheng²,

Li³

et al. 2021

Preprint

View full text Add to dashboard Cite

Recommender system is one of the most important information services on today's Internet. Recently, graph neural networks have become the new state-of-the-art approach of recommender systems. In this survey, we conduct a comprehensive review of the literature in graph neural network-based recommender systems. We first introduce the background and the history of the development of both recommender systems and graph neural networks. For recommender systems, in general, there are four aspects for categorizing existing works: stage, scenario, objective, and application. For graph neural networks, the existing methods consist of two categories, spectral models and spatial ones. We then discuss the motivation of applying graph neural networks into recommender systems, mainly consisting of the high-order connectivity, the structural property of data, and the enhanced supervision signal. We then systematically analyze the challenges in graph construction, embedding propagation/aggregation, model optimization, and computation efficiency. Afterward and primarily, we provide a comprehensive overview of a multitude of existing works of graph neural network-based recommender systems, following the taxonomy above. Finally, we raise discussions on the open problems and promising future directions of this area. We summarize the representative papers along with their codes repositories in https://github.com/tsinghua-fib-lab/GNN-Recommender-Systems.

show abstract

“…Recently, some research [12,24,27] have conducted sequential recommendations based on KGs and user-item interactions. For instance, Baocheng et al [24] use a hybrid of graph neural network and a key-value memory network to extract users' sequential interest and semantic-based preference, which improves the strategy for constructing session graphs from interaction sequences for the sequential recommendation task. To solve the user-commodity sparseness in , a knowledge-guided reinforcement learning model is proposed, which designs a composite reward function to compute both sequence and knowledge level rewards.…”

Section: Sequential Explainable Recommendationmentioning

confidence: 99%

Reinforced KGs reasoning for explainable sequential recommendation

et al. 2021

View full text Add to dashboard Cite

We explore the semantic-rich structured information derived from the knowledge graphs (KGs) associated with the user-item interactions and aim to reason out the motivations behind each successful purchase behavior. Existing works on KGs-based explainable recommendations focus purely on path reasoning based on current useritem interactions, which generally result in the incapability of conjecturing users' subsequence preferences. Considering this, we attempt to model the KGs-based explainable recommendation in sequential settings. Specifically, we propose a novel architecture called Reinforced Sequential Learning with Gated Recurrent Unit (RSL-GRU), which is composed of a Reinforced Path Reasoning Network (RPRN) component and a GRU component. RSL-GRU takes users' sequential behaviors and their associated KGs in chronological order as input and outputs potential top-N items for each user with appropriate reasoning paths from a global perspective. Our RPRN features a remarkable path reasoning capacity, which is regulated by a userconditioned derivatively action pruning strategy, a soft reward strategy based on an improved multi-hop scoring function, and a policy-guided sequential path reasoning algorithm. Experimental results on four of Amazon's large-scale datasets show that our method achieves excellent results compared with several state-of-the-art alternatives. Powered by Editorial Manager® and ProduXion Manager® from Aries Systems CorporationAlthough the time complexity of our model is a little higher in the worst situation than Ω 2 in DAN, KPRN, and KARN, its calculation is much smaller compared with them. Point 2.Datasets in section 5.1.1 need to be given the links or citations.Thank you for your suggestion. We add a link (https://nijianmo.github.io/amazon/index.html) to the datasets in section 5.1.1 on page 13.Noname manuscript No.

show abstract

Knowledge-Enhanced Graph Neural Networks for Sequential Recommendation

Cited by 23 publications

References 25 publications

Sequential Modeling with Multiple Attributes for Watchlist Recommendation in E-Commerce

Sequential Modeling with Multiple Attributes for Watchlist Recommendation in E-Commerce

A Survey of Graph Neural Networks for Recommender Systems: Challenges, Methods, and Directions

Reinforced KGs reasoning for explainable sequential recommendation

Contact Info

Product

Resources

About