arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2011.02100cs.IRcs.CY
收藏

去振荡图协同过滤

Deoscillated Graph Collaborative Filtering

Zhiwei Liu, Lin Meng, Fei Jiang, Jiawei Zhang, Philip S. Yu

摘要:

协同过滤(CF)信号是推荐系统(RS)学习用户和项目嵌入的关键。高阶信息可以缓解基于CF的方法的冷启动问题,其通过在用户-项目二分图上传播信息来建模。最近的图神经网络~(GNN)提出堆叠多个聚合层来传播高阶信号。然而,振荡问题,二部图的变化的局部性,以及固定的传播模式破坏了多层结构的信息传播能力。振荡问题是由二分结构引起的,因为来自用户的信息只传播到项目。除了振荡问题外,变化的局部性表明在传播过程中应该考虑节点的密度。此外,层固定传播模式在层之间引入冗余信息。为了解决这些问题,我们提出了一种新的RS模型,命名为\textbf{D} eoscillated \textbf{G}和\textbf{C} ollabative \textbf{F} filtering ~(DGCF)。我们在其中引入跨跳传播层,打破了二分传播结构,从而解决了振荡问题。此外,我们设计了创新的局部自适应层,自适应地传播信息。DGCF模型通过堆叠多个跨跳传播层和局部性层,自适应地对节点和层的局部性建模高阶CF信号。在真实数据集上的大量实验表明了DGCF的有效性。详细的分析表明,DGCF解决了振荡问题,自适应学习局部因子,并具有逐层传播模式。我们的代码可在https://github.com/JimLiu96/DeosciRec上获得。

英文摘要:

Collaborative Filtering (CF) signals are crucial for a Recommender System~(RS) model to learn user and item embeddings. High-order information can alleviate the cold-start issue of CF-based methods, which is modelled through propagating the information over the user-item bipartite graph. Recent Graph Neural Networks~(GNNs) propose to stack multiple aggregation layers to propagate high-order signals. However, the oscillation problem, varying locality of bipartite graph, and the fix propagation pattern spoil the ability of multi-layer structure to propagate information. The oscillation problem results from the bipartite structure, as the information from users only propagates to items. Besides oscillation problem, varying locality suggests the density of nodes should be considered in the propagation process. Moreover, the layer-fixed propagation pattern introduces redundant information between layers. In order to tackle these problems, we propose a new RS model, named as \textbf{D}eoscillated \textbf{G}raph \textbf{C}ollaborative \textbf{F}iltering~(DGCF). We introduce cross-hop propagation layers in it to break the bipartite propagating structure, thus resolving the oscillation problem. Additionally, we design innovative locality-adaptive layers which adaptively propagate information. Stacking multiple cross-hop propagation layers and locality layers constitutes the DGCF model, which models high-order CF signals adaptively to the locality of nodes and layers. Extensive experiments on real-world datasets show the effectiveness of DGCF. Detailed analyses indicate that DGCF solves oscillation problem, adaptively learns local factor, and has layer-wise propagation pattern. Our code is available online at https://github.com/JimLiu96/DeosciRec.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑