%0 Journal Article %1 8290687 %A He, L. %A Shao, B. %A Xiao, Y. %A Li, Y. %A Liu, T. %A Chen, E. %A Xia, H. %D 2018 %J IEEE Transactions on Big Data %K deep_learning knowledge_graph monte-carlo semantic %P 1-1 %R 10.1109/TBDATA.2018.2805363 %T Neurally-Guided Semantic Navigation in Knowledge Graph %U https://ieeexplore.ieee.org/document/8290687/#full-text-section %X In this big data era, knowledge becomes increasingly linked, along with the rapid growth in data volume. Connected knowledge is naturally represented and stored as knowledge graphs, which are of great importance for many frontier research areas. Effectively finding relations between entities in large knowledge graphs plays a key role in many knowledge graph applications, as the most valuable part of a knowledge graph is its rich connectedness, which captures rich information about the real-world objects. However, due to the intrinsic complexity of real-world knowledge, finding semantically close relations by navigation in a large knowledge graph is challenging. Canonical graph exploration methods inevitably result in combinatorial explosion especially when the paths connecting two entities are long: the search space is <formula><tex>$O(d^l)$</tex></formula>, where <formula><tex>$d$</tex></formula> is the average graph node degree and l is the path length. In this paper, we will systematically study the semantic navigation problem for large knowledge graphs. Inspired by AlphaGo, which was overwhelmingly successful in game Go, we designed an efficient semantic navigation method based on a well-tailored Monte Carlo Tree Search algorithm with the unique characteristics of knowledge graphs considered. Extensive experiments show that our method is not only effective but also very efficient.

@article{8290687, abstract = {In this big data era, knowledge becomes increasingly linked, along with the rapid growth in data volume. Connected knowledge is naturally represented and stored as knowledge graphs, which are of great importance for many frontier research areas. Effectively finding relations between entities in large knowledge graphs plays a key role in many knowledge graph applications, as the most valuable part of a knowledge graph is its rich connectedness, which captures rich information about the real-world objects. However, due to the intrinsic complexity of real-world knowledge, finding semantically close relations by navigation in a large knowledge graph is challenging. Canonical graph exploration methods inevitably result in combinatorial explosion especially when the paths connecting two entities are long: the search space is <formula><tex>$O(d^l)$</tex></formula>, where <formula><tex>$d$</tex></formula> is the average graph node degree and l is the path length. In this paper, we will systematically study the semantic navigation problem for large knowledge graphs. Inspired by AlphaGo, which was overwhelmingly successful in game Go, we designed an efficient semantic navigation method based on a well-tailored Monte Carlo Tree Search algorithm with the unique characteristics of knowledge graphs considered. Extensive experiments show that our method is not only effective but also very efficient.}, added-at = {2018-09-10T11:01:16.000+0200}, author = {He, L. and Shao, B. and Xiao, Y. and Li, Y. and Liu, T. and Chen, E. and Xia, H.}, biburl = {https://www.bibsonomy.org/bibtex/227114fc23b0541e1ba683ad919f6040b/dallmann}, description = {Neurally-Guided Semantic Navigation in Knowledge Graph - IEEE Journals & Magazine}, doi = {10.1109/TBDATA.2018.2805363}, interhash = {7c309841b237cfaccb9d8bbe65428ae0}, intrahash = {27114fc23b0541e1ba683ad919f6040b}, issn = {2332-7790}, journal = {IEEE Transactions on Big Data}, keywords = {deep_learning knowledge_graph monte-carlo semantic}, pages = {1-1}, timestamp = {2018-09-10T11:01:16.000+0200}, title = {Neurally-Guided Semantic Navigation in Knowledge Graph}, url = {https://ieeexplore.ieee.org/document/8290687/#full-text-section}, year = 2018 }