Knowledge Graph Reasoning通俗的理解,所谓推理,就是从现有的知识出发,运用逻辑思维能力,得出一些隐性的结论。具体到知识图谱中,所谓的知识推理,就是利用图谱中现有的知识(三元组),得到一些新的实体间的关系或者实体的属性(三元组)。设想一下,假如机器推理做的完备,一方面,它能够帮我们填充知识图谱中大量的空缺,使得知识更为完备;另一方面,对于知识问答、推荐系统等任务也有非常大的加成。
ICLR, (2020)
We evaluate QUERY2BOX on three standard Knowledge graphs benchmarks and show: QUERY2BOX provides strong generalization as it can answer complex queries; QUERY2BOX can generalize to new logical query structures that it has never seen during training; QUERY2BOX is able to implicitl...
Cited by20BibtexViews944
0
0
IJCAI 2020, pp.1926-1932, (2020)
Experimental results show our model demonstrates competitive performance compared with existing knowledge graph completion methods
Cited by2BibtexViews620DOI
0
0
NIPS 2020, (2020)
We have presented Beta Embedding, the first embedding-based method that could handle arbitrary first-order logic queries on knowledge graph
Cited by1BibtexViews172
0
0
Meng Qu, Junkun Chen, Louis-Pascal Xhonneux,Yoshua Bengio,Jian Tang
international conference on learning representations, (2020)
Learn Logic Rules for Reasoning on Knowledge Graphs.
Cited by0BibtexViews198
0
0
EMNLP 2020, pp.5694-5703, (2020)
In order to solve this problem, we propose a reinforcement learning model named DacKGR with two strategies designed for sparse knowledge graph
Cited by0BibtexViews196DOI
0
0
international conference on machine learning, (2020)
We showed that Conditional Theorem Provers are scalable and yield state-of-the-art results on the CLUTRR dataset, which explicitly tests the systematic generalisation of neural models, in comparison with a wide set of neural baselines
Cited by0BibtexViews188
0
0
EMNLP 2020, pp.8541-8547, (2020)
Walk-based models have shown their advantages in knowledge graph (KG) reasoning by achieving decent performance while providing interpretable decisions. However, the sparse reward signals offered by the KG during a traversal are often insufficient to guide a sophisticated walk-ba...
Cited by0BibtexViews175DOI
0
0
Marcel Hildebrandt, Jorge Andres Quintero Serna, Yunpu Ma,Martin Ringsquandl, Mitchell Joblin,Volker Tresp
national conference on artificial intelligence, (2020)
We proposed R2D2, a new approach for Knowledge graphs reasoning based on a debate game between two opposing reinforcement learning agents
Cited by0BibtexViews79
0
0
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019), (2019): 7710-7720
We propose the probabilistic Logic Neural Network, which combines the advantages of both methods
Cited by29BibtexViews191
0
0
WWW '19: The Web Conference on The World Wide Web Conference WWW 2019, (2019): 2366-2377
We want to explore following questions: 1) whether axioms really help sparse entity embedding learning? To do this, we evaluate the quality of embeddings on link prediction task which is widely applied in previous knowledge graph embedding works; 2) whether embeddings really help...
Cited by15BibtexViews317DOI
2
0
Xin Lv, Yuxian Gu,Xu Han,Lei Hou,Juanzi Li,Zhiyuan Liu
EMNLP/IJCNLP (1), pp.3374-3379, (2019)
We propose a meta-learning based model named Meta-KGR for multi-hop reasoning over few-shot relations of knowledge graphs
Cited by13BibtexViews197DOI
0
0
Cong Fu, Tong Chen,Meng Qu,Woojeong Jin,Xiang Ren
EMNLP/IJCNLP (1), pp.2672-2681, (2019)
We focus on a new task named as Open Knowledge Graph Reasoning, which aims at boosting the knowledge graph reasoning with new knowledge extracted from the background corpus
Cited by8BibtexViews123DOI
0
0
Ali Sadeghian, Mohammadreza Armandpour, Patrick Ding,Daisy Zhe Wang
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019), (2019): 15321-15331
We present DRUM, a fully differentiable rule mining algorithm which can be used for inductive and interpretable link prediction
Cited by3BibtexViews66
0
0
Ruiping Li,Xiang Cheng
EMNLP/IJCNLP (1), pp.2642-2651, (2019)
We present DIVINE, a novel plug-and-play framework based on generative adversarial imitation learning for enhancing existing reinforcement learning-based methods
Cited by0BibtexViews76DOI
0
0
Heng Wang, Shuangyin Li,Rong Pan, Mingzhi Mao
EMNLP/IJCNLP (1), pp.2623-2631, (2019)
We propose AttnPath, a Deep Reinforcement Learning based model for Knowledge Graph reasoning task which incorporates LSTM and Graph Attention Mechanism as memory components, to alleviate the model from pretraining
Cited by0BibtexViews137DOI
0
0
international conference on learning representations, (2018)
We achieve state-of-the-art results on multiple benchmark knowledge base completion tasks and we show that our model is robust and can learn long chains-ofreasoning
Cited by185BibtexViews497
1
0
national conference on artificial intelligence, (2018)
Many traditional approaches for Knowledge graph-powered Question answering are based on semantic parsers, which first map a question to formal meaning representation and translate it to a Knowledge graph query
Cited by131BibtexViews415
0
0
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 31 (NIPS 2018), (2018): 2030-2041
We introduce a framework to efficiently make predictions about conjunctive logical queries—a flexible but tractable subset of first-order logic—on incomplete knowledge graphs
Cited by73BibtexViews235
0
0
north american chapter of the association for computational linguistics, (2018)
We propose a novel variational inference framework for knowledge graph reasoning
Cited by57BibtexViews127DOI
0
0
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 31 (NIPS 2018), (2018): 6787-6798
We developed an reinforcement learning-agent that learns to walk over a graph towards a desired target node for given input query and source nodes
Cited by48BibtexViews183
0
0