Link prediction by exploiting network formation games in exchangeable graphs

Wang, Liqiang; Wang, Yafang; Liu, Bin; Li-rong, HE; Liu, Shijun; Melo, Gerard de; Xu, Zenglin

doi:10.1109/ijcnn.2017.7965910

Cited by 4 publications

(1 citation statement)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since each block is much smaller than the whole subgraph G R K , it would be faster if we excavate the KGs information in each block using the well-designed RPRN. It is noted that we ignore the relations between each block, which has been proved that it can effectively increase the computing speed with no loss to the final results [25]. As shown in Fig.…”

Section: Sequential Kgs Building Using Blocking Strategymentioning

confidence: 96%

Reinforced KGs reasoning for explainable sequential recommendation

et al. 2021

Self Cite

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

Section: Sequential Kgs Building Using Blocking Strategymentioning

confidence: 96%