Adapting Distilled Knowledge for Few-Shot Relation Reasoning over Knowledge Graphs
Adapting Distilled Knowledge for Few-Shot Relation Reasoning over Knowledge Graphs
复制标题
采用蒸馏知识进行知识图上的少样本关系推理
DOI：
10.1137/1.9781611977172.75
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Zhang, Chuxu
中科院分区：
文献类型：
--
作者：
Zhang, Yiming;Qian, Yiyue;Ye, Yanfang;Zhang, Chuxu
知识图(KGs)是语义搜索、问答或对话生成等应用的重要资源。作为多跳KG推理的基本任务之一，多跳KG推理的目的是通过推理路径产生有效的、可解释的关系预测。目前的方法往往需要为每个查询关系提供足够数量的训练数据(即事实三元组)，这损害了它们在KGS中常见的少射关系(具有有限数据)上的适用性和性能。尽管已经提出了一些稀疏关系推理方法，但它们的有效性和效率仍有待提高。为了解决这些问题，我们提出了一种新的基于KGS的多跳少镜头关系推理模型ADK-KG。在ADK-KG中，我们引入了一个强化学习框架来建模顺序推理过程。我们进一步开发了一种文本增强的异构图神经网络来编码节点嵌入，其中实体和关系嵌入是使用内容信息来预训练的。随后，我们使用了一种任务感知的元学习算法来优化模型参数，这些参数可以快速适应于少镜头关系。进一步设计了知识提炼模块，利用未标注数据改进模型训练。在三个基准数据集上的大量实验表明，ADK-KG具有令人满意的效率，并且性能优于最先进的方法。
Knowledge graphs (KGs) are serving as important resources for many applications, such as semantic search, question answering, or dialogue generation. As one of the fundamental tasks, multi-hop KG reasoning aims at generating effective and explainable relation prediction through reasoning paths. The current methods often require sufficient amount of training data (i.e., fact triples) for each query relation, impairing their applicabilities and performances over few-shot relations (with limited data) which are common in KGs. Despite that some few-shot relation reasoning methods have been proposed, their effectiveness and efficiency remain to be improved. To address these challenges, we propose a novel model called ADK-KG for multi-hop few-shot relation reasoning over KGs. In ADK-KG, we introduce a reinforcement learning framework to model the sequential reasoning process. We further develop a text-enhanced heterogeneous graph neural network to encode node embeddings, where entity and relation embeddings are pre-trained using content information. Later, we employ a task-aware meta-learning algorithm to optimize the model parameters that could be fast adapted for few-shot relations. A knowledge distillation module is further designed to make use of unlabeled data for improving model training. Extensive experiments on three benchmark datasets demonstrate that ADK-KG has satisfactory efficiency and outperforms state-of-the-art approaches.