[深度学习] KGAT：Knowledge Graph Attention Network for Recommendation.pdf

说明： Toprovidemoreaccurate,diverse,andexplainablerecommendation, it is compulsory to go beyond modeling user-item interactions andtakesideinformationintoaccount.Traditionalmethodslike factorizationmachine(FM)castitasasupervisedlearningproblem, whichassum
<qq_31367595> 上传 | 大小：1mb

[深度学习] Jointly Learning Explainable Rules for Recommendation with Knowledge Graph.pdf

说明： Explainabilityandeffectivenessaretwokeyaspectsforbuildingrecommendersystems.Prioreffortsmostlyfocusonincorporatingside informationtoachievebetterrecommendationperformance.However,thesemethodshavesomeweaknesses:(1)predictionofneural network-basedembe
<qq_31367595> 上传 | 大小：1mb

[深度学习] Iteratively Learning Embeddings and Rules for Knowledge Graph Reasoning.pdf

说明： Reasoning is essential for the development of large knowledge graphs,especiallyforcompletion,whichaimstoinfernewtriples basedonexistingones.Bothrulesandembeddingscanbeusedfor knowledgegraphreasoningandtheyhavetheirownadvantages anddifficulties.Rule-
<qq_31367595> 上传 | 大小：1mb

[深度学习] Investigating Robustness and LinkPredictionAdversarialModifications.pdf

说明： Representing entities and relations in an embedding space is a well-studied approach for machine learning on relational data. Existing approaches, however, primarily focus on improving accuracy and overlook other aspects such as robustness and inter
<qq_31367595> 上传 | 大小：417kb

[深度学习] Graph Adversarial Training：Dynamically Regularizing Based on Graph Structure.pdf

说明： Abstract—Recent efforts show that neural networks are vulnerable to small but intentional perturbations on input features in visual classification tasks. Due to the additional consideration of connections between examples (e.g., articles with citatio
<qq_31367595> 上传 | 大小：1mb

[深度学习] Fake News Detection via NLP is Vulnerable to Adversarial Attacks.pdf

说明： News plays a significant role in shaping people’s beliefs and opinions. Fake news has always been a problem, which wasn’t exposed to the mass public until the past election cycle for the 45th President of the United States. While quite a few detectio
<qq_31367595> 上传 | 大小：685kb

[深度学习] ERNIE：Enhanced Language Representation with Informative Entities.pdf

说明： Neural language representation models such as BERT pre-trained on large-scale corpora can well capture rich semantic patterns from plaintext,andbefine-tunedtoconsistentlyimprove the performance of various NLP tasks. However, the existing pre-trained
<qq_31367595> 上传 | 大小：1mb

[深度学习] Enhancement of Power Equipment Management Using Knowledge Graph.pdf

说明： Abstract—Accurate retrieval of the power equipment information plays an important role in guiding the full-lifecycle management of power system assets. Because of data duplication, database decentralization, weak data relations, and sluggish data up
<qq_31367595> 上传 | 大小：2mb

[深度学习] End-to-End Knowledge-Routed Relational Dialogue SystemforAutomaticDiagnosis.pdf

说明： Beyond current conversational chatbots or task-oriented dialogue systems that have attracted increasing attention, we move forward to develop a dialogue system for automatic medical diagnosis that converses with patients to collect additional sympto
<qq_31367595> 上传 | 大小：424kb

[深度学习] Defeats GAN：A Simpler Model Outperforms in Knowledge Representation Learning.pdf

说明： Abstract—The goal of knowledge representation learning is to embed entities and relations into a low-dimensional, continuous vector space. How to push a model to its limit and obtain better results is of great significance in knowledge graphs appli
<qq_31367595> 上传 | 大小：348kb

[深度学习] Cyber-All-Intel：An AI for Security related Threat Intelligence.pdf

说明： In this paper we present, Cyber-All-Intel an artificial intelligence system to aid a security analyst. It is a system for knowledge extraction, representation and analytics in an end-toend pipeline grounded in the cybersecurity informatics domain. It
<qq_31367595> 上传 | 大小：1mb

[深度学习] Context-Aware Embeddings for Automatic Art Analysis.pdf

说明： Automaticartanalysisaimstoclassifyandretrieveartisticrepresentationsfromacollectionofimagesbyusingcomputervision andmachinelearningtechniques.Inthiswork,weproposetoenhancevisualrepresentationsfromneuralnetworkswithcontextual artisticinformation.Wher
<qq_31367595> 上传 | 大小：5mb