可解释的知识图谱推理方法综述

doi:10.11959/j.issn.2096-109x.2022063

Abstract

Abstract:

In recent years, deep learning models have achieved remarkable progress in the prediction and classification tasks of artificial intelligence systems.However, most of the current deep learning models are black box, which means it is not conducive to human cognitive reasoning process.Meanwhile, with the continuous breakthroughs of artificial intelligence in the researches and applications, high-performance complex algorithms, models and systems generally lack the transparency and interpretability of decision making.This makes it difficult to apply the technologies in a wide range of fields requiring strict interpretability, such as national defense, medical care and cyber security.Therefore, the interpretability of artificial intelligence should be integrated into these algorithms and systems in the process of knowledge reasoning.By means of carrying out explicit explainable intelligence reasoning based on discrete symbolic representation and combining technologies in different fields, a behavior explanation mechanism can be formed which is an important way for artificial intelligence to realize data perception to intelligence perception.A comprehensive review of explainable knowledge graph reasoning was given.The concepts of explainable artificial intelligence and knowledge reasoning were introduced briefly.The latest research progress of explainable knowledge graph reasoning methods based on the three paradigms of artificial intelligence was introduced.Specifically, the ideas and improvement process of the algorithms in different scenarios of explainable knowledge graph reasoning were explained in detail.Moreover, the future research direction and the prospect of explainable knowledge graph reasoning were discussed.

Key words: knowledge reasoning, knowledge graph, explainable artificial intelligence, information security

CLC Number:

TP309

Yi XIA, Mingjng LAN, Xiaohui CHEN, Junyong LUO, Gang ZHOU, Peng HE. Survey on explainable knowledge graph reasoning methods[J]. Chinese Journal of Network and Information Security, 2022, 8(5): 1-25.

Figures/Tables 19

三元组和基本规则	一阶逻辑的格式
$(h, r, t)$	$r (h) = > t$
$(h, r_{1}, t) = > (h, r_{2}, t)$	$\begin{array}{l} [(h \in C) \land [r_{1} (h) = > t]] \\ = > [r_{2} (h) = > t] \end{array}$
$\begin{array}{l} (e_{1}, r_{1}, e_{2}) + (e_{2}, r_{2}, e_{3}) \\ = > (e_{1}, r_{3}, e_{3}) \end{array}$	$\begin{array}{l} [[r_{1} (e_{1}) = > e_{2}] \land [r_{2} (e_{2}) = > e_{3}]] \\ = > [r_{3} (e_{1}) = > e_{3}] \end{array}$
$(h, r_{1}, t) < = > (t, r_{2}, h)$	$\begin{array}{l} [[r_{1} (h) = > t] = > [r_{2} (t) = > h]] \land \\ [[r_{2} (t) = > h] = > [r_{1} (h) = > t]] \end{array}$

一阶逻辑	数学表达
$r (h)$	$r + h$
$a = > b$	$a - b$
$h \in C$	$h \cdot C (C 是一个矩阵)$
$a \land b$	$a \otimes b$
$a < = > b$	$(a - b) \otimes (a - b)$

分类	子分类	部分经典模型	推理特点	推理准确性（MRR）	解释形式	可解释的范围	可解释的产生方法	可解释的泛化性
		Pellet(2007)^[38]
	基于本体的	OP(2016)^[43]	利用抽象化本体层面的		本体的演绎	全局可
	知识推理	JOIE(2019)^[46]	频繁模式、约束或路径	—	关系	解释	事前可解释	模型无关
符号主义中的知识推理		OntoED(2021)^[44]	进行推理
符号主义中的知识推理		MLN(2006)^[54]		0.098
	基于逻辑规则	AIME+(2015)^[52]	通过挖掘全局或局部逻	0.292	逻辑规则	全局可	事前可解释	模型无关
	的知识推理	AnyBURL(2020)^[64]	辑规则或特征进行推理	0.346		解释
		Rule-IC(2021)^[66]		0.355
		PRA(2010)^[66]		0.098	计算推理路
	基于随机游走	SFE(2015)^[69]	通过随机游走发现隐式	0.232	径特征的权	局部可	事前可解释	模型无关
	的知识推理	TRWA(2018)^[70]	的关联规则，但是搜索	0.359	重为结果进	解释
行为主义中的知识推理		Attnpath(2019)^[71]	空间较大，计算效率低	0.346	行解释
行为主义中的知识推理		DeepPath(2018)^[73]	缓解了基于随机游走搜	0.301	借助强化学
	基于强化学习	MINERVA(2018)^[74]	索空间过大的问题，但	0.298	习的推理路	局部可	事前可解释	解释特定
	的知识推理	MultiHop(2018)^[76]	黑盒模型的引入导致可	0.363	径来解释智	解释		于模型
		SparKGR(2022)^[80]	解释性下降	0.385	能体的行为
		TransE(2013)^[87]		0.326
	基于平移距离	RotateE(2019)^[91]		0.338		局部可	事后可解释	解释特定
	的模型	DuelE(2021)^[94]	利用知识图谱表示模	0.492	关系模式、逻	解释		于模型
连接主义中的知识推理		MuRP(2020)^[99]	型，将实体和关系映射	0.418	辑操作、实体
连接主义中的知识推理		RESCAL(2015)^[100]	为低维向量，数值化计	0.227	的层次关系
	基于张量分解	DisMult(2016)^[101]	算进行推理预测	0.312		局部可	事后可解释	解释特定
	的模型	ASNALOGY(2019)^[103]		0.356		解释		于模型
		TuckER(2020)^[104]		0.409
		KALE(2016)^[114]	充分利用规则的准确性	0.312
	符号规则增强	PlogicNet(2019)^[124]	高、可解释性强的优势，	0.332	逻辑规则推	局部可	事后可解释	解释特定
	神经网络的知	ExpressGNN(2020)^[125]	提高神经网络推理的透	0.420	理路径	解释		于模型
新型混合的知识推理	识推理	UniKER(2021)^[118]	明性及可靠性	0.522
新型混合的知识推理		Neural LP(2017)^[129]	充分利用神经网络鲁棒	0.237
	神经网络增强	RLvLR(2019)^[137]	性和效率上的优势，缓	0.24	关系模式逻	全局可	事前可解释	模型无关
	符号规则的知	NLIL(2020)^[131]	解数据噪声及搜索空间	0.26	辑操作实体	解释
	识推理	RNNLogic(2021)^[140]	大的问题	0.344	的层次关系
注：由于符号主义中基于本体的知识推理为概念层的推理，推理准确率不以比较。

References 142

[22]	AUER S , BIZER C , KOBILAROV G ,et al. Dbpedia:a nucleus for a Web of open data[M]// Proceedings of the Semantic Web. Berlin: Springer, 2007.
[23]	BOLLACKER K , EVANS C , PARITOSH P ,et al. Freebase:a collaboratively created graph database for structuring human knowledge[C]// Proceedings of the 2008 ACM SIGMOD Int Conf on Management of Data. 2008: 1247-1250.
[24]	HU S , ZOU L , YU J X ,et al. Answering natural language questions by subgraph matching over knowledge graphs[J]. IEEE Trans on Knowledge and Data Engineering, 2017,30(5): 824-837.
[25]	PALUMBO E , RIZZO G , TRONCY R . Entity2rec:learning user-item relatedness from knowledge graphs for top-n item recommendation[C]// Proceedings of the 7th ACM Conf on Recommender Systems. 2017: 32-36.
[26]	宋蕾, 马春光, 段广晗 . 机器学习安全及隐私保护研究进展[J]. 网络与信息安全学报, 2018,4(8): 1-11.
	SONG L , MA C G , DUAN G H . Machine learning security and privacy:a survey[J]. Chinese Journal of Network and Information Security, 2018,4(8): 1-11.
[27]	任奎, 孟泉润, 闫守琨 ,等. 人工智能模型数据泄露的攻击与防御研究综述[J]. 网络与信息安全学报, 2021,7(1): 1-10.
	REN K , MENG Q R , YAN S K ,et al. Survey of artificial intelligence data security and privacy protection[J]. Chinese Journal of Network and Information Security, 2021,7(1): 1-10.
[28]	BADER S , GRANGEL-GONZALE Z , NANJAPPA P ,et al. A knowledge graph for industry 4.0[C]// Proceedings of the 2020 European Semantic Web Conf. 2020: 465-480.
[29]	ISA B , MSBC D . Open-CyKG:an open cyber threat intelligence knowledge graph[J]. Knowledge-Based Systems, 2021,233:107524.
[1]	RISSOLA E A , BAHRAINIAN S A , CRESTANI F . Personality recognition in conversations using capsule neural networks[C]// Proceedings of the Int Conf on Web Intelligence. 2019: 180-187.
[2]	SADAK F , SAADAT M , HAJIYAVAND A M . Real-time deep learning-based image recognition for applications in automated positioning and injection of biological cells[J]. Computers in Biology and Medicine, 2020,125(10): 103976.
[30]	刘知远, 孙茂松, 林衍凯 ,等. 知识表示学习研究进展[J]. 计算机研究与发展, 2016,53(2): 247-261.
	LIU Z Y , SUN M S , LIN Y K ,et al. Knowledge representation learning:a review[J]. Journal of Computer Research and Development, 2016,53(2): 247-261.
[3]	VALMADRE J , BERTINETTO L , HENRIQUES J ,et al. End-to-end representation learning for correlation filter based tracking[C]// Proceedings of the IEEE Conf on Computer Vision and Pattern Recognition. 2017: 2805-2813.
[4]	MILLEN J . A survey of methods for explaining black box models[J]. Computing Reviews, 2019,60(4): 175-176.
[31]	LECUE , FREDDY . On the role of knowledge graphs in explainable AI[J]. Semantic Web, 2020,11(1): 41-51.
[32]	刘峤, 李杨, 段宏 ,等. 知识图谱构建技术综述[J]. 计算机研究与发展, 2016,53(3): 582-600.
[5]	DOSHI-VELEZ F , KIM B . Towards a rigorous science of interpretable machine learning[J]. arXiv preprint arXiv:1702.08608, 2017.
[6]	ZHANG Y U , TINO P , LEONARDIS A ,et al. A survey on neural network interpretability[J]. arXiv preprint arXiv:2012.14261, 2021.
[32]	LIU Q , LI Y , DUAN H ,et al. Knowledge graph construction techniques[J]. Journal of Computer Research and Development, 2016,53(3): 582-600.
[33]	刘潇, 刘书洋, 庄韫恺 ,等. 强化学习可解释性基础问题探索和方法综述[J]. 软件学报, 2021.
[7]	成科扬, 王宁, 师文喜 ,等. 深度学习可解释性研究进展[J]. 计算机研究与发展, 2020,57(6): 1208-1217.
	CHENG K Y , WANG N , SHI W X ,et al. Research advances in the interpretability of deep learning[J]. Journal of Computer Research and Development, 2020,57(6): 1208-1217.
[8]	GAWEHN E , HISS J A , SCHNEIDER G . Deep learning in drug discovery[J]. Molecular Informatics, 2016,35(1): 3-14.
[9]	方滨兴 . 定义网络空间安全[J]. 网络与信息安全学报, 2018,4(1): 1-5.
	FANG B X . Define cyberspace security[J]. Chinese Journal of Network and Information Security, 2018,4(1): 1-5.
[10]	HOFMAN J M , SHARMA A , WATTS D J . Prediction and explanation in social systems[J]. Science, 2017,355(6324): 486-488.
[11]	胡浩, 刘玉岭, 张玉臣 ,等. 基于攻击图的网络安全度量研究综述[J]. 网络与信息安全学报, 2018,4(9): 1-16.
	HU H , LIU Y L , ZHANG Y C ,et al. Survey of attack graph based network security metric[J]. Chinese Journal of Network and Information Security, 2018,4(9): 1-16.
[33]	LIU X , LIU S Y , ZHUANG W K ,et al. Explainable reinforcement learning:basic problems exploration and a survey[J]. Journal of Software, 2021.
[34]	EHRLINGER L , WOLFRAM W . Towards a definition of knowledge graphs[C]// Proceedings of the Posters and Demos Track of 12th International Conference on Semantic Systems - SEMANTiCS2016 and 1st International Workshop on Semantic Change ＆Evolving Semantics (SuCCESS16). 2016.
[12]	CHEN X , JIA S , XIANG Y . A review:knowledge reasoning over knowledge graph[J]. Expert Systems with Application, 2020,141(3): 1-21.
[13]	AMIT S . Introducing the knowledge graph[R]. America:Official Blog of Google, 2012.
[35]	CHEN X , CHEN H J , ZHANG N Y ,et al. OWL reasoning over big biomedical data[C]// Proceedings of the 2013 IEEE Int Conf on Big Data. 2013: 29-36.
[36]	ZHANG D H , YUAN Z X , LIU H ,et al. Learn to walk with dual agents for knowledge graph reasoning[C]// Proceedings of the 2022 AAAI Conf on Artificial Intelligence. 2022: 5932-5941.
[14]	DAVID G , MARK S , JAESIK C ,et al. XAI-Explainable artificial intelligence[J]. Science Robotics, 2019,4(37): 7120.
[15]	官赛萍, 靳小龙, 贾岩涛 ,等. 面向知识图谱的知识推理研究进展[J]. 软件学报, 2018,29(10): 2966-2994.
[37]	ZOU Y , FININ T , CHEN H . F-OWL:an inference engine for semantic Web[C]// Proceedings of the Int Conf on Formal Approaches to Agent-based Systems. 2004: 238-248.
[38]	SIRIN E , PARSIA B , GRAU B C ,et al. Pellet:a practical OWL DL reasoner[J]. Journal of Web Semantics, 2007,5(2): 51-53.
[15]	GUAN S P , JIN X L , JIA Y T ,et al. Knowledge reasoning over knowledge graph:a survey[J]. Journal of Software, 2018,29(10): 2966-2994.
[16]	WANG Q , MAO Z , WANG B ,et al. Knowledge graph embedding:a survey of approaches and applications[J]. IEEE Transactions on Knowledge and Data Engineering, 2017,29(12): 2724-2743.
[39]	WEI Y Z , LUO J , XIE H Y . KGRL:an OWL2 RL reasoning system for large scale knowledge graph[C]// Proceedings of the 12th Int Conf on Semantics,Knowledge and Grids. 2016: 83-89.
[40]	ZHOU J , MA L , LIU Q ,et al. Minerva:a scalable OWL ontology storage and inference system[C]// Proceedings of the Asian Conf on the Semantic Web. 2006: 429-443.
[41]	SOMA R , PRASANNA V K . Parallel inferencing for OWL knowledge bases[C]// Proceedings of the 37th Int Conf on Parallel Processing. 2008: 75-82.
[42]	MARX M , KR?TZSCH M , THOST V . Logic on mars:ontologies for generalised property graphs[C]// Proceedings of the 26th Int Joint Conf on Artificial Intelligence. 2017: 118-1194.
[43]	CHEN Y , GOLDBERG S , WANG D Z ,et al. Ontological pathfinding:mining first-order knowledge from large knowledge bases[C]// Proceedings of the 2016 Int Conf on Management of Data. 2016: 835-846.
[44]	HAO J H , CHEN M H , YU W C ,et al. Universal representation learning of knowledge bases by jointly embedding instances and ontological concepts[C]// Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery ＆ Data Mining (KDD '19). 2019: 1709-1719.
[45]	KULMANOV M , LIU-WEI W , YAN Y ,et al. El Embeddings:geometric construction of models for the description logic el++[C]// Proceedings of the 28th International Joint Conference on Artificial Intelligence (IJCAI-19). 2019: 6103-6109.
[46]	DENG S , ZHANG N , LI L ,et al. Ontoed:low-resource event detection with ontology embedding[J]. arXiv preprint arXiv:2105.10922, 2021.
[17]	ARORA S . A Survey on graph neural networks for knowledge graph completion[J]. arXiv preprint arXiv:2007.12374, 2020.
[18]	LIPTON Z C . The mythos of model interpretability[J]. Communications of the ACM, 2016,61(10): 31-57.
[47]	SCHOENMACKERS S , ETZIONI O , WELD D S ,et al. Learningfirst-order horn clauses from Web text[C]// Proceedings of the 2010 Conf on Empirical Methods in Natural Language Processing. 2010: 1088-1098.
[48]	LANDWEHR N , KERSTING K , RAEDT L D . Integrating naive Bayes and FOIl[J]. Journal of Machine Learning Research, 2007,8(5): 481-507.
[19]	KRIZHEVSKY A , SUTSKEVER I , HINTON G E . Imagenet classification with deep convolutional neural networks[J]. Advances in Neural Information Processing Systems, 2012,25(2): 84-90.
[20]	PAPERNOT N , MCDANIEL P , JHA S ,et al. The limitations of deep learning in adversarial settings[C]// Proceedings of 2016 IEEE European Symp on Security and Privacy. 2016: 372-387.
[49]	LANDWEHR N , PASSERINI A , RAEDT L D ,et al. Fast learning of relational kernels[J]. Machine Learning, 2010,78(3): 305-342.
[50]	NAKASHOLE N , SOZIO M , SUCHANEK F M ,et al. Query-time reasoning in uncertain RDF knowledge bases with soft and hard rules[J]. VLDS, 2012,884(6): 15-20.
[51]	GALáRRAGA L , TELIOUDI C , HOSE K ,et al. Fast rule mining in ontological knowledge bases with AMIE+[J]. The Int Journal on Very Large Data Bases, 2015,24(6): 707-730.
[52]	GALáRRAGA L , TELIOUDI C , HOSE K ,et al. Amie:association rule mining under incomplete evidence in ontological knowledge bases[C]// Proceedings of the 22nd Int Conf on World Wide Web. 2013: 413-422.
[53]	WANG Z C , LI J Z . RDF2Rules:learning rules from RDF knowledge bases by mining frequent predicate cycles[J]. arXiv preprint arXiv:1512.07734, 2015.
[54]	KOK S , DOMINGOS P . Learning the structure of Markov logic networks[C]// Proceedings of the 22nd Int Conf on Machine Learning. 2005: 441-448.
[55]	RICHARDSON M , DOMINGOS P . Markov logic networks[J]. Machine Learning, 2006,62(1-2): 107-136.
[56]	ONDREJ K , JESSE D . Markov logic networks for knowledge base completion:a theoretical analysis under the MCAR assumption[C]// Proceedings of the 35th Uncertainty in Artificial Intelligence Conf. 2020: 1138-1148.
[57]	DE-RAEDT L , KIMMIG A , TOIVONEN H . A probabilistic prolog and its application in link discovery[C]// Proceedings of the 20th Int Joint Conf on Artifical Intelligence. 2007: 2462-2467.
[58]	CUSSENS J . Parameter estimation in stochastic logic programs[J]. Machine Learn, 2001,44(3): 245-271.
[59]	WANG W Y , MAZAITIS K , COHEN W W . Programming with personalized pagerank:a locally groundable first-order probabilistic logic[C]// Proceedings of the 22nd ACM Int Conf on Information ＆Knowledge Management. 2013: 2129-2138.
[60]	HAVELIWALA T H . Topic-sensitive PageRank:a context-sensitive ranking algorithm for Web search[J]. IEEE Trans on Knowledge and Data Engineering, 2003,15(4): 784-796.
[61]	KIMMIG A , BACH S H , BROECHELER M ,et al. A short introduction to probabilistic soft logic[C]// Proceedings of the NIPS Workshop on Probabilistic Programming:Foundations and Applications. 2012: 1-4.
[62]	PUJARA J , MIAO H , GETOOR L ,et al. Ontology-aware partitioning for knowledge graph identification[C]// Proceedings the Workshop on Automated Knowledge Base Construction. 2013: 19-24.
[63]	BACH S H , BROECHELER M , HUANG B ,et al. Hinge-loss markov random fields and probabilistic soft logic[J]. Computer Science, 2017,18(1): 1-67.
[64]	MEILICKE C , CHEKOL M W , FINK M ,et al. Reinforced anytime bottom up rule learning for knowledge graph completion[J]. arXiv preprint,arXiv:2004.04412, 2020.
[65]	PEDRESCHI D , GIANNOTTI F , GUIDOTTI R ,et al. Meaningful explanations of black box ai decision systems[C]// Proceedings of the AAAI Conf on Artificial Intelligence. 2019.
[66]	LAO N , COHEN W . Relational retrieval using a combination of path-constrained random walks[J]. Machine Learning, 2010,81(1): 53-67.
[67]	LAO N , MITCHELL T , COHEN W . Random walk inference and learning in a large scale knowledge base[C]// Proceedings of the 2011 Conf on Empirical Methods in Natural Language Processing. 2011: 27-31.
[68]	GARDNER M , TALUKDAR P , KRISHNAMURTHY J ,et al. Incorporating vector space similarity in random walk inference over knowledge bases[C]// Proceedings of the 2014 Conf on Empirical Methods in Natural Language Processing. 2014: 397-406.
[69]	GARDNER M , MITCHELL T . Efficient and expressive knowledge base completion using subgraph feature extraction[C]// Proceedings of the 2015 Conf on Empirical Methods in Natural Language Processing. 2015: 1488-1498.
[70]	LIU Q , HAN M , JIANG L ,et al. Two-tier random walk based relational inference algorithm[J]. Chineses Journal of Computers, 2017,40(6): 1275-1290.
[71]	WEI Z , ZHAO J , LIU K . Mining inference formulas by goal-directed random walks[C]// Proceedings of the 2016 Conf on Empirical Methods in Natural Language Processing. 2016: 1379-1388.
[72]	WANG Q , LIU J , LUO Y F ,et al. Knowledge base completion via coupled path ranking[C]// Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics. 2016: 1308-1318.
[73]	XIONG W H , HONG T , WANG W Y . DeepPath:a reinforcement learning method for knowledge graph reasoning[C]// Proceedings of the 2017 Conf on Empirical Methods in Natural Language Processing. 2017: 564-573.
[74]	DAS R , DHULIAWALA S , ZAHEER M ,et al. Go for a walk and arrive at the answer:reasoning over paths in knowledge bases using reinforcement learning[C]// Proceedings of the 6th Int Conf on Learning Representations. 2018.
[75]	GREFF K , SRIVASTAVA R K , KOUTNíK J , ,et al. LSTM:a search space odyssey[J]. IEEE Trans on Neural Networks ＆Learning Systems, 2016,28(10): 2222-2232.
[76]	LIN X V , SOCHER R , XIONG C M . Multi- hop knowledge graph reasoning with reward shaping[C]// Proceedings of the 2018 Conf on Empirical Methods in Natural Language Processing. 2018: 3243-3253.
[77]	SHEN Y , CHEN J , HUANG P S ,et al. M-Walk:learning to walk over graphs using monte carlo tree search[C]// Proceedings of the 32nd Int Conf on Neural Information Processing Systems. 2018: 6786-6797.
[78]	GODIN F , KUMAR A , MITTAL A . Using ternary rewards to reason over knowledge graphs with deep reinforcement learning[C]// Proceedings of the 2019 Conf and Workshop on Neural Information Processing Systems. 2019: 846-852.
[79]	LEI D R , JIANG G G , GU X T ,et al. Learning collaborative agents with rule guidance for knowledge graph reasoning[C]// Proceedings of the 2020 Conf on Empirical Methods in Natural Language Processing. 2020: 8541-8547.
[80]	XIA Y , LAN M J , LUO J Y ,et al. Iterative rule-guided reasoning over sparse knowledge graphs with deep reinforcement learning[C]// Information Processing ＆ Management. 2022:103040.
[81]	CHEN W H , XIONG W H , YAN X F ,et al. Variational knowledge graph reasoning[C]// Proceedings of the 2018 Conf of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies. 2018: 1823-1832.
[82]	KINGMA D P , WELLING M . Auto-encoding variational Bayes[C]// Proceedings of the 2nd Int Conf on Learning Representations. 2014: 1-14.
[83]	LI Z X , JINX L , GUAN S P ,et al. Path reasoning over knowledge graph:a multi-agent and reinforcement learning based method[C]// Proceedings of the 2018 IEEE Int Conf on Data Mining Workshops. 2018: 929-936.
[84]	YU W T , MA X G , BAI L Y ,et al. Path-based knowledge graph completion combining reinforcement learning with soft rules[C]// Proceedings of the Int Conf on Natural Computation,Fuzzy Systems and Knowledge Discovery. 2019: 139-146.
[85]	WANG Q , HAO Y S , CAO J . ADRL:an attention-based deep reinforcement learning framework for knowledge graph reasoning[J]. Knowledge-Based Systems, 2020,197(7): 105910.
[86]	HILDEBRANDT M , SERNA J A Q , MA Y P ,et al. Reasoning on knowledge graphs with debate dynamics[C]// Proceedings of the 34th AAAI Conf on Artificial Intelligence. 2020: 4123-4131.
[87]	BORDES A , USUNIER N , GARCIADURAN A ,et al. Translating embeddings for modeling multi-relational data[C]// Proceedings of the 26th Int Conf on Neural Information Processing Systems. 2013: 2787-2795.
[88]	WANG Z , ZHANG J W , FENG J L ,et al. Knowledge graph embedding by translating on hyper planes[C]// Proceedings of the 28th AAAI Conf on Artificial Intelligence. 2014: 1112-1119.
[89]	LIN Y K , LIU Z Y , SUN M S ,et al. Learning entity and relation embeddings for knowledge graph completion[C]// Proceedings of the 29th AAAI Conf on Artificial Intelligence. 2015: 2181-2187.
[90]	JI G , LIU K , HE S ,et al. Knowledge graph completion with adaptive sparse transfer matrix[C]// Proceedings of the 30th AAAI Conference on Artificial Intelligence. 2016: 985-991.
[91]	SUN Z Q , DENG Z H , NIE J Y ,et al. RotatE:knowledge graph embedding by relational rotation in complex space[C]// Proceedings of the 7th Int Conf on Learning Representations. 2019.
[92]	ZHANG S , TAY Y , YAO L ,et al. Quaternion knowledge graph embeddings[C]// Proceedings of the 33rd Conference on Neural Information Processing Systems. 2019: 1-14.
[93]	SONG T W , LUO J , HUANG L . Rot-Pro:modeling transitivity by projection in knowledge graph embedding[J]. Advances in Neural Information Processing Systems, 2021,34.
[94]	CAO Z S , XU Q Q , YANG Z Y et al . Dual quaternion knowledge graph embeddings[C]// Proceedings of the AAAI Conference on Artificial Intelligence. 2021: 6894-6902.
[95]	LI M , JIA Y , WANG Y ,et al. Hierarchy-based link prediction in knowledge graphs[C]// Proceedings of the 25th International Conference Companion on World Wide Web. 2016: 77-78.
[96]	ZHANG Z , CAI J , ZHANG Y ,et al. Learning hierarchy-aware knowledge graph embeddings for link prediction[C]// Proceedings of the AAAI Conference on Artificial Intelligence. 2020: 3065-3072.
[97]	WANG S , FU K , SUN X ,et al. Hierarchical-aware relation rotational knowledge graph embedding for link prediction[J]. Neurocomputing, 2021,458: 259-270.
[98]	HU Z , HUANG P , DENG Y ,et al. Entity hierarchy embedding[C]// Proceedings of the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing. 2015: 1292-1300.
[99]	BALAZEVIC I , ALLEN C , HOSPEDALES T . Multi-relational poincaré graph embeddings[J]. Advances in Neural Information Processing Systems, 2019,32: 4463-4473.
[100]	NICKEL M , TRESP V , KRIEGEL H-P . A three-way model for collective learning on multi-relational data[C]// Proceedings of the Int Conf on Machine Learning. 2011: 809-816.
[101]	YANG B , YI W T , HE X ,et al. Embedding entities and relations for learning and inference in knowledge bases[C]// Proceedings of the 2015 Int Conf on Learning Representations. 2015.
[102]	TROUILLON T , WELBL J , RIEDEL S ,et al. Complex embeddings for simple link prediction[C]// Proceedings of the Int Conf on Machine Learning. 2016: 2071-2080.
[103]	LIU H , WU Y , YANG Y . Analogical inference for multi-relational embeddings[C]// Proceedings of the International Conference on Machine Learning. 2017: 2168-2178.
[104]	BALA?EVI? I , ALLEN C , HOSPEDALES T M . Tucker:tensor factorization for knowledge graph completion[J]. arXiv preprint arXiv:1901.09590, 2019.
[105]	SOCHER R , CHEN D , MANNING C D ,et al. Reasoning with neural tensor networks for knowledge base completion[C]// Proceedings of the Advances in Neural Information Processing Systems. 2013: 926-934.
[106]	BORDES A , GLOROT X , WESTON J ,et al. A semantic matching energy function for learning with multi-relational data[J]. Machine Learning, 2014,94(2): 233-259.
[107]	LIU Q , JIANG H , Evdokimov A ,et al. Probabilistic reasoning via deep learning:neural association models[J]. arXiv preprint arXiv:1603.07704, 2016.
[108]	DETTMERS T , MINERVINI P , STENETORP P ,et al. Convolutional 2D knowledge graph embeddings[C]// Proceedings of the 32nd AAAI Conference on Artificial Intelligence. 2018: 1811-1818.
[109]	VU T , NGUYEN T D , NGUYEN D Q ,et al. A capsule network-based embedding model for knowledge graph completion and search personalization[C]// Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies. 2019: 2180-2189.
[110]	VASHISHTH S , SANYAL S , NITIN V ,et al. InteractE:improving convolution-based knowledge graph embeddings by increasing feature interactions[C]// Proceedings of the AAAI Conference on Artificial Intelligence. 2020: 3009-3016.
[111]	YAO L , MAO C , LUO Y . KG-BERT:BERT for knowledge graph completion[J]. arXiv preprint arXiv:1909.03193, 2019.
[112]	ZHAO Y , ZHOU H , XIE R B ,et al. Incorporating global information in local attention for knowledge representation learning[C]// Proceedings of the Findings of the Association for Computational Linguistics:ACL-IJCNLP 2021. 2021: 1341-1351.
[113]	姚思雨, 赵天哲, 王瑞杰 ,等. 规则引导的知识图谱联合嵌入方法[J]. 计算机研究与发展, 2020,57(12): 2514-2522.
	YAO S Y , ZHAO T Z , WANG R J ,et al. Rule-guided joint embedding learning of knowledge graphs[J]. Journal of Computer Research and Development, 2020,57(12): 2514-2522.
[114]	GUO S , WANG Q , WANG L H ,et al. Jointly embedding knowledge graphs and logical rules[C]// Proceedings of the 2016 Conf on Empirical Methods in Natural Language Processing. 2016: 192-202.
[115]	GUO S , WANG Q , WANG L H ,et al. Knowledge graph embedding with iterative guidance from soft rules[C]// Proceedings of the 32th AAAI Conf on Artificial Intelligence. 2018: 4816-4823.
[116]	WANG P W , DOU D J , WU F Z ,et al. Logic rules powered knowledge graph embedding[J]. arXiv preprint,arXiv:1903.03772, 2019.
[117]	ZHANG W , PAUDEL B , WANG L ,et al. Iteratively learning embeddings and rules for knowledge graph reasoning[C]// Proceedings of the World Wide Web Conf. 2019: 2366-2377.
[21]	SUCHANEK F M , KASNECI G , WEIKUM G . Yago:a core of semantic knowledge[C]// Proceedings of the 16th Int Conf on World Wide Web. 2007: 697-706.
[118]	CHENG K W , YANG Z Q , ZHANG M ,et al. UniKER:a unified framework for combining embedding and definite horn rule reasoning for knowledge graph inference[C]// Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. 2021: 9753-9771.
[119]	NEELAKANTAN A , ROTH B , MCCALLUM A . Compositional vector space models for knowledge base completion[J]. Computer Science, 2015: 1-16.
[120]	SHEN Y , HUANG P S , CHANG M W ,et al. Traversing knowledge graph in vector space without symbolic space guidance[J]. arXiv preprint,arXiv:1611.04642, 2016.
[121]	DAS R , NEELAKANTAN A , BELANGER D ,et al. Chains of reasoning over entities,relations,and text using recurrent neural networks[C]// Proceedings of the 15th Conf of the European Chapter of the Association for Computational Linguistics. 2017: 132-141.
[122]	WANG Z K , LI L J , ZENG D D . Attention-based multi-hop reasoning for knowledge graph[C]// Proceedings of the 2018 IEEE Int Conf on Intelligence and Security Informatics. 2018: 211-213.
[123]	NIU G , ZHANG Y , LI B ,et al. Rule-guided compositional representation learning on knowledge graphs[C]// Proceedings of the AAAI Conference on Artificial Intelligence. 2020: 2950-2958.
[124]	QU M , TANG J . Probabilistic logic neural networks for reasoning[C]// Proceedings of the Advances in Neural Information Processing Systems. 2019: 7712-7722.
[125]	ZHANG Y Y , CHEN X S , YANG Y ,et al. Efficient probabilistic logic reasoning with graph neural networks[J]. arXiv preprint,arXiv:2001.11850, 2020.
[126]	VARDHAN L V H , JIA G , KOK S . Probabilistic logic graph attention networks for reasoning[C]// Proceedings of the World Wide Web Conf 2020. 2020: 669-673.
[127]	COHEN W W . Tensorlog:a differentiable deductive database[J]. arXiv preprint,arXiv:1605.06523, 2020.
[128]	EVANS R , GREFENSTETTE E . Learning explanatory rules from noisy data[J]. Journal of Artificial Intelligence Research, 2018,61(8): 1-64.
[129]	YANG F , YANG Z , COHEN W W . Differentiable learning of logical rules for knowledge base reasoning[C]// Proceedings of the Advances in Neural Information Processing Systems. 2017: 2319-2328.
[130]	WANG P , STEPANOVA D , DOMOKOS C ,et al. Differentiable learning of numerical rules in knowledge graphs[C]// Proceedings of the 8th Int Conf on Learning Representations. 2020.
[131]	YAN Y , SONG L . Learn to explain efficiently via neural logic inductive learning[C]// Proceedings of the 8th Int Conf on Learning Representations. 2020.
[132]	WANG S , WEI X K , NOGUEIRA DOS SANTOS C N ,et al. Mixed-curvature multi-relational graph neural network for knowledge graph completion[C]// Proceedings of the Web Conference. 2021: 1761-1771.
[133]	TERU K K , DENIS E , HAMILTON W L . Inductive relation prediction by subgraph reasoning[J]. arXiv preprint,arXiv:1911.06962, 2019.
[134]	DU Z , ZHOU C , DING M ,et al. Cognitive knowledge graph reasoning for one-shot relational learning[J]. IEEE Trans on Knowledge and Data Engineering, 2021.
[135]	XU X R , FENG W , JIANG Y S ,et al. Dynamically pruned message passing networks for large-scale knowledge graph reasoning[C]// Proceedings of the 2020 Int Conf on Learning Representations. 2020.
[136]	HO V T , STEPANOVA D , GAD-ELRAB M H ,et al. Rule learning from knowledge graphs guided by embedding models[C]// Proceedings of the 17th Int Semantic Web Conf. 2018: 72-90.
[137]	OMRAN P G , WANG K , WANG Z . Scalable rule learning via learning representation[C]// Proceedings of the 27th Int Joint Conf on Artificial Intelligence. 2018: 2149-2155.
[138]	DONG H H , MAO J Y , LIN T ,et al. Neural logic machines[C]// Proceedings of the 7th Int Conf on Learning Reresentations. 2019.
[139]	PAN Y , LIU J , ZHANG L ,et al. Learning first-order rules with relational path contrast for inductive relation reasoning[J]. arXiv preprint arXiv:2110.08810, 2021.
[140]	QU M , CHEN J K , XHONNEUX L P ,et al. RNNLogic:learning logic rules for reasoning on knowledge graphs[C]// Proceedings of the 2021 Int Conf on Learning Representations. 2021.
[141]	XIA Y , ZHOU G , LUO J Y ,et al. PFCA:an intelligent method of multidimensional user profile construction and application[C]// Proceedings of the 2022 Int Conf on big data analytics. 2022: 272-279.
[142]	LYU X , CAO Y X , HOU L ,et al. Is multi-hop reasoning really explainable? Towards benchmarking reasoning interpretability[C]// Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. 2021: 8899-8911.

Metrics

Recommended 0

No Suggested Reading articles found!

Survey on explainable knowledge graph reasoning methods

RichHTML

PDF下载

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 19

References 142

Related Articles 15

Metrics

Recommended 0

分类	部分经典模型	推理特点推理准确性（MRR）	推理准确性（Hit@3）	解释形式	可解释的范围	可解释的产生方式	可解释的泛化性	下游场所适用性
	Pellet(2007)^[38]
基于本体的	OP(2016)^[43]	利用抽象化本体层		本体的演	全局	事前可		可靠性
知识推理	JOIE(2019)^[46]	面的频繁模式、约—	—	绎关系	可解释	解释	模型无关	优先领域
	OntoED(2021)^[44]	束或路径进行推理
	MLN(2006)^[54]	0.098	0.103
基于逻辑规则	AIME+(2015)^[52	通过挖掘全局或局0.292	0.305		全局	事前可		可靠性
的知识推理	AnyBURL(2020)^[64]	部逻辑规则或特征0.346	0.367	逻辑规则	可解释	解释	模型无关	优先领域
	Rule-IC(2021)^[66]	进行推理0.355	0.374
注：由于符号主义中基于本体的知识推理为概念层的推理，推理准确性不做比较。

[1]	Xiaochen SHEN, Yinhui GE, Bo CHEN, Ling YU. Research on construction technology of artificial intelligence security knowledge graph [J]. Chinese Journal of Network and Information Security, 2023, 9(2): 164-174.
[2]	Ganqin LIU, Hui LI, Hui ZHU, Yukun HUANG, Xingdong LIU. Public key cryptographic algorithm SM2 optimized implementation on low power embedded platform [J]. Chinese Journal of Network and Information Security, 2022, 8(6): 29-38.
[3]	Jun LIU, Lin YUAN, Zhishang FENG. Survey of key management schemes for cluster networks [J]. Chinese Journal of Network and Information Security, 2022, 8(6): 52-69.
[4]	Cheng SUN, Hao HU, Yingjie YANG, Hongqi ZHANG. Prediction method of 0day attack path based on cyber defense knowledge graph [J]. Chinese Journal of Network and Information Security, 2022, 8(1): 151-166.
[5]	Rongna XIE, Xiaonan FAN, Lin YUAN, Zichen GUO, Jiayu ZHU, Guozhen SHI. Research on extended access control mechanism in online social network [J]. Chinese Journal of Network and Information Security, 2021, 7(5): 123-131.
[6]	Jin LI, Jin CAO, Yueyu ZHANG, Meiru ZHANG, Hui LI. Reverse teaching design of curriculum ideological and political in information security major—Take the wireless communication network security course of Xidian University as an example [J]. Chinese Journal of Network and Information Security, 2021, 7(3): 166-174.
[7]	Guojie LIU,Jianbiao ZHANG. TPCM-based trusted PXE boot method for servers [J]. Chinese Journal of Network and Information Security, 2020, 6(6): 105-111.
[8]	Qiao HU,Yupeng HU,Xin LIAO,Zheng QIN,Jianhua SUN,Jiliang ZHANG. Investigation,analysis and improvement mentality of the revision on information security’s training program to undergraduates in Hunan University [J]. Chinese Journal of Network and Information Security, 2020, 6(4): 153-158.
[9]	Qiang QU,Hongtao YU,Ruiyang HUANG. Attention-based approach of detecting spam in social networks [J]. Chinese Journal of Network and Information Security, 2020, 6(1): 54-61.
[10]	JIA Chunfu,LI Ruiqi,TIAN Meiqi,CHENG Xiaoyang. Discuss on cultivating mode of information security and law inter-disciplinary talents [J]. Chinese Journal of Network and Information Security, 2019, 5(3): 31-35.
[11]	Jinxin ZUO,Ziyu GUO,Jin LI,Jie ZHANG,Yueming LU. Security evaluation method for confidential and stable complex systems [J]. Chinese Journal of Network and Information Security, 2019, 5(2): 58-65.
[12]	Shudi CHEN,Youwen ZHU. Shoulder-surfing resistant PIN-entry method [J]. Chinese Journal of Network and Information Security, 2019, 5(1): 87-93.
[13]	Ying CHENG. Data protection impact assessment system in the mode of risk management [J]. Chinese Journal of Network and Information Security, 2018, 4(8): 63-70.
[14]	Yuehang DING, Hongtao YU, Ruiyang HUANG, Yingle LI. Ontology summarization technology survey [J]. Chinese Journal of Network and Information Security, 2018, 4(10): 12-21.
[15]	Zenan WU,Liqin TIAN,Zhigang WANG. Behavior authentication of Web users based on machine learning [J]. Chinese Journal of Network and Information Security, 2018, 4(1): 45-51.

分类	部分经典模型	推理特点	推理准确性（MRR）	推理准确性（Hit@3）	解释形式	可解释的范围	可解释的产生方式	可解释的泛化性	下游式场景适应性
	PRA(2010)^[67]	通过随机游走发现隐	0.098	0.197
基于随机	SFE(2015)^[69]	式的关联规则，但搜	0.232	0.307	计算推理路径
游走的知	TRWA(2018)^[70]	索空间较大，计算效	0.359	0.359	特征的权重为	局部	事前		效率优先领
识推理	Attnpath(2019)^[71]	率低	0.346	0.391	结果进行解释	可解释	可解释	模型无关	域
	DeepPath(2018)^[73]	缓解了基于随机游走	0.301	0.381	借助强化学习
基于强化	MINERVA(2018)^[74]	搜索空间过大的问	0.298	0.389	的推理路径来	局部	事前	解释特定	效率优先领
学习的知	MultiHop(2018)^[76]	题，但黑盒模型的引	0.363	0.413	解释智能体的	可解释	可解释	于模型	域
识推理	Ruleguider(2022)^[79]	入导致可解释性下降	0.385	0.438	行为