当前位置: X-MOL 学术arXiv.cs.IR › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Inductive Representation Based Graph Convolution Network for Collaborative Filtering
arXiv - CS - Information Retrieval Pub Date : 2021-07-12 , DOI: arxiv-2107.05247
Yunfan Wu, Qi Cao, Huawei Shen, Shuchang Tao, Xueqi Cheng

In recent years, graph neural networks (GNNs) have shown powerful ability in collaborative filtering, which is a widely adopted recommendation scenario. While without any side information, existing graph neural network based methods generally learn a one-hot embedding for each user or item as the initial input representation of GNNs. However, such one-hot embedding is intrinsically transductive, making these methods with no inductive ability, i.e., failing to deal with new users or new items that are unseen during training. Besides, the number of model parameters depends on the number of users and items, which is expensive and not scalable. In this paper, we give a formal definition of inductive recommendation and solve the above problems by proposing Inductive representation based Graph Convolutional Network (IGCN) for collaborative filtering. Specifically, we design an inductive representation layer, which utilizes the interaction behavior with core users or items as the initial representation, improving the general recommendation performance while bringing inductive ability. Note that, the number of parameters of IGCN only depends on the number of core users or items, which is adjustable and scalable. Extensive experiments on three public benchmarks demonstrate the state-of-the-art performance of IGCN in both transductive and inductive recommendation scenarios, while with remarkably fewer model parameters. Our implementations are available here in PyTorch.

中文翻译:

用于协同过滤的基于归纳表示的图卷积网络

近年来,图神经网络(GNN)在协同过滤方面表现出强大的能力,这是一种广泛采用的推荐场景。虽然没有任何辅助信息,但现有的基于图神经网络的方法通常会为每个用户或项目学习一个单热嵌入作为 GNN 的初始输入表示。然而,这种 one-hot 嵌入本质上是转导的,使得这些方法没有归纳能力,即无法处理训练过程中看不见的新用户或新项目。此外,模型参数的数量取决于用户和项目的数量,这是昂贵且不可扩展的。在本文中,我们给出了归纳推荐的正式定义,并通过提出基于归纳表示的图卷积网络(IGCN)用于协同过滤来解决上述问题。具体来说,我们设计了一个归纳表示层,它利用与核心用户或项目的交互行为作为初始表示,在提高一般推荐性能的同时带来归纳能力。需要注意的是,IGCN 的参数数量仅取决于核心用户或项目的数量,这是可调整和可扩展的。在三个公共基准上的大量实验证明了 IGCN 在转导和归纳推荐场景中的最先进性能,同时模型参数明显减少。我们的实现在 PyTorch 中可用。提升一般推荐性能的同时带来归纳能力。需要注意的是,IGCN 的参数数量仅取决于核心用户或项目的数量,这是可调整和可扩展的。在三个公共基准上的大量实验证明了 IGCN 在转导和归纳推荐场景中的最先进性能,同时模型参数明显减少。我们的实现在 PyTorch 中可用。提升一般推荐性能的同时带来归纳能力。需要注意的是,IGCN 的参数数量仅取决于核心用户或项目的数量,这是可调整和可扩展的。在三个公共基准上的大量实验证明了 IGCN 在转导和归纳推荐场景中的最先进性能,同时模型参数明显减少。我们的实现在 PyTorch 中可用。
更新日期:2021-07-13
down
wechat
bug