Zobrazeno 1 - 10
of 99
pro vyhledávání: '"GRAU, BERNARDO CUENCA"'
Graph neural networks (GNNs) are frequently used to predict missing facts in knowledge graphs (KGs). Motivated by the lack of explainability for the outputs of these models, recent work has aimed to explain their predictions using Datalog, a widely u
Externí odkaz:
http://arxiv.org/abs/2408.10261
DatalogMTL is an extension of Datalog with metric temporal operators that has found an increasing number of applications in recent years. Reasoning in DatalogMTL is, however, of high computational complexity, which makes reasoning in modern data-inte
Externí odkaz:
http://arxiv.org/abs/2401.02869
We introduce negation under the stable model semantics in DatalogMTL - a temporal extension of Datalog with metric temporal operators. As a result, we obtain a rule language which combines the power of answer set programming with the temporal dimensi
Externí odkaz:
http://arxiv.org/abs/2306.07625
Knowledge Graph (KG) completion is the problem of extending an incomplete KG with missing facts. A key feature of Machine Learning approaches for KG completion is their ability to learn inference patterns, so that the predicted facts are the results
Externí odkaz:
http://arxiv.org/abs/2306.04814
Although there has been significant interest in applying machine learning techniques to structured data, the expressivity (i.e., a description of what can be learned) of such techniques is still poorly understood. In this paper, we study data transfo
Externí odkaz:
http://arxiv.org/abs/2305.18015
DatalogMTL is an extension of Datalog with metric temporal operators that has found applications in temporal ontology-based data access and query answering, as well as in stream reasoning. Practical algorithms for DatalogMTL are reliant on materialis
Externí odkaz:
http://arxiv.org/abs/2208.07100
Autor:
Wang, Dingmin, Liu, Shengchao, Wang, Hanchen, Grau, Bernardo Cuenca, Song, Linfeng, Tang, Jian, Le, Song, Liu, Qi
Graph Neural Networks (GNNs) are effective tools for graph representation learning. Most GNNs rely on a recursive neighborhood aggregation scheme, named message passing, thereby their theoretical expressive power is limited to the first-order Weisfei
Externí odkaz:
http://arxiv.org/abs/2206.00362
In recent years, there has been increasing interest in explanation methods for neural model predictions that offer precise formal guarantees. These include abductive (respectively, contrastive) methods, which aim to compute minimal subsets of input f
Externí odkaz:
http://arxiv.org/abs/2205.09901
DatalogMTL is an extension of Datalog with operators from metric temporal logic which has received significant attention in recent years. It is a highly expressive knowledge representation language that is well-suited for applications in temporal ont
Externí odkaz:
http://arxiv.org/abs/2201.04596
Double-descent curves in neural networks describe the phenomenon that the generalisation error initially descends with increasing parameters, then grows after reaching an optimal number of parameters which is less than the number of data points, but
Externí odkaz:
http://arxiv.org/abs/2102.07238