Graph Collaborative Reasoning
Graph Collaborative Reasoning
复制标题
DOI：
10.1145/3488560.3498410
复制
发表时间：
2021-12
期刊：
影响因子：
--
通讯作者：
H. Chen;Yunqi Li;Shaoyun Shi;Shuchang Liu;He Zhu;Yongfeng Zhang
中科院分区：
文献类型：
--
作者：
H. Chen;Yunqi Li;Shaoyun Shi;Shuchang Liu;He Zhu;Yongfeng Zhang
图可以表示实体之间的关系信息，图结构广泛应用于搜索、推荐、问答等智能任务中。然而，实际中的大多数图结构数据都存在不完备性问题，因此链接预测成为一个重要的研究问题。虽然人们提出了许多链接预测模型，但对以下两个问题的探讨还很少：(1)大多数方法没有利用相关链接的丰富信息对每个链接进行独立建模；(2)现有模型大多是基于联想学习设计的，没有考虑推理。针对这些问题，本文提出了图协同推理(GCR)，它可以从逻辑推理的角度利用图上的邻接链信息进行关系推理。我们提供了一种简单的方法将图结构转换为逻辑表达式，从而将链接预测任务转化为神经逻辑推理问题。根据逻辑表达式，应用逻辑约束神经模块构建网络结构，利用反向传播算法有效学习模型参数，将可微学习和符号推理连接在一个统一的体系结构中。为了证明我们的工作的有效性，我们在常用的基准数据集上进行了链接预测和推荐等与图相关的任务的实验，我们的图协同推理方法获得了最先进的性能。
Graphs can represent relational information among entities and graph structures are widely used in many intelligent tasks such as search, recommendation, and question answering. However, most of the graph-structured data in practice suffer from incompleteness, and thus link prediction becomes an important research problem. Though many models are proposed for link prediction, the following two problems are still less explored: (1) Most methods model each link independently without making use of the rich information from relevant links, and (2) existing models are mostly designed based on associative learning and do not take reasoning into consideration. With these concerns, in this paper, we propose Graph Collaborative Reasoning (GCR), which can use the neighbor link information for relational reasoning on graphs from logical reasoning perspectives. We provide a simple approach to translate a graph structure into logical expressions so that the link prediction task can be converted into a neural logic reasoning problem. We apply logical constrained neural modules to build the network architecture according to the logical expression and use backpropagation to efficiently learn the model parameters, which bridges differentiable learning and symbolic reasoning in a unified architecture. To show the effectiveness of our work, we conduct experiments on graph-related tasks such as link prediction and recommendation based on commonly used benchmark datasets, and our graph collaborative reasoning approach achieves state-of-the-art performance.