A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit <a rel="external noopener" href="https://mdpi-res.com/d_attachment/information/information-13-00229/article_deploy/information-13-00229.pdf?version=1651230256">the original URL</a>. The file type is <code>application/pdf</code>.
A Multi-Granular Aggregation-Enhanced Knowledge Graph Representation for Recommendation
<span title="2022-04-29">2022</span>
<i title="MDPI AG">
<a target="_blank" rel="noopener" href="https://fatcat.wiki/container/dmr4kpn2yreovpdxpdiqtjcrnu" style="color: black;">Information</a>
</i>
Preserved Fulltext
Knowledge graph (KG) helps to improve the accuracy, diversity, and interpretability of a recommender systems. KG has been applied in recommendation systems, exploiting graph neural networks (GNNs), but most existing recommendation models based on GNNs ignore the influence of node types and the loss of information during aggregation. In this paper, we propose a new model, named A Multi-Granular Aggregation-Enhanced Knowledge Graph Representation for Recommendation (MAKR), that relieves the
<span class="external-identifiers">
<a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/info13050229">doi:10.3390/info13050229</a>
<a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/k4fqottd3vaoncy5r7kgdty4zi">fatcat:k4fqottd3vaoncy5r7kgdty4zi</a>
</span>
more »
... ty of the network and overcomes the limitation of information loss of the traditional GNN recommendation model. Specifically, we propose a new graph, named the Improved Collaborative Knowledge Graph (ICKG), that integrates user–item interaction and a knowledge graph into a huge heterogeneous network, divides the nodes in the heterogeneous network into three categories—users, items, and entities, and connects the edges according to the similarity between the users and items so as to enhance the high-order connectivity of the graph. In addition, we used attention mechanisms, the factorization machine (FM), and transformer (Trm) algorithms to aggregate messages from multi-granularity and different types to improve the representation ability of the model. The empirical results of three public benchmarks showed that MAKR outperformed state-of-the-art methods such as Neural FM, RippleNet, and KGAT.
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220501025651/https://mdpi-res.com/d_attachment/information/information-13-00229/article_deploy/information-13-00229.pdf?version=1651230256" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext">
<button class="ui simple right pointing dropdown compact black labeled icon button serp-button">
<i class="icon ia-icon"></i>
Web Archive
[PDF]
<div class="menu fulltext-thumbnail">
<img src="https://blobs.fatcat.wiki/thumbnail/pdf/76/1f/761fa98c629115f1b694797ae910920e9021b29d.180px.jpg" alt="fulltext thumbnail" loading="lazy">
</div>
</button>
</a>
<a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/info13050229">
<button class="ui left aligned compact blue labeled icon button serp-button">
<i class="unlock alternate icon" style="background-color: #fb971f;"></i>
mdpi.com
</button>
</a>