paper-with-me

홈 › Papers

DIVINE: A Generative Adversarial Imitation Learning Framework for Knowledge Graph Reasoning

2019-11-01 · IJCNLP 2019 11 · Ruiping Li, Xiang Cheng

Knowledge graphs (KGs) often suffer from sparseness and incompleteness. Knowledge graph reasoning provides a feasible way to address such problems. Recent studies on knowledge graph reasoning have shown that reinforcement learning (RL) based methods can provide state-of-the-art performance. However, existing RL-based methods require numerous trials for path-finding and rely heavily on meticulous reward engineering to fit specific dataset, which is inefficient and laborious to apply to fast-evolving KGs. To this end, in this paper, we present DIVINE, a novel plug-and-play framework based on generative adversarial imitation learning for enhancing existing RL-based methods. DIVINE guides the path-finding process, and learns reasoning policies and reward functions self-adaptively through imitating the demonstrations automatically sampled from KGs. Experimental results on two benchmark datasets show that our framework improves the performance of existing RL-based methods while eliminating extra reward engineering.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Imitation LearningKnowledge GraphsReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

A Deep Generative Model of Vowel Formant Typology

2018-07-08 · NAACL 2018 6 · Ryan Cotterell, Jason Eisner

What makes some types of languages more probable than others? For instance, we know that almost all spoken languages contain the vowel phoneme /i/; why should that be? The field of linguistic typology seeks to answer the…

Payoff Information and Learning in Signaling Games

2020-01-14

We add the assumption that players know their opponents' payoff functions and rationality to a model of non-equilibrium learning in signaling games. Agents are born into player roles and play against random opponents eve…

Active Learning

Adversarial Imitation Attack

2020-03-28 · Mingyi Zhou, Jing Wu, Yipeng Liu, Xiaolin Huang 외

Deep learning models are known to be vulnerable to adversarial examples. A practical adversarial attack should require as little as possible knowledge of attacked models. Current substitute attacks need pre-trained model…

Adversarial Attack

DIVINE: Diverse Influential Training Points for Data Visualization and Model Refinement

2021-07-13 · Umang Bhatt, Isabel Chien, Muhammad Bilal Zafar, Adrian Weller

As the complexity of machine learning (ML) models increases, resulting in a lack of prediction explainability, several methods have been developed to explain a model's behavior in terms of the training data points that m…

Data VisualizationFairness

Integration of Imitation Learning using GAIL and Reinforcement Learning using Task-achievement Rewards via Probabilistic Graphical Model

2019-07-03 · Akira Kinose, Tadahiro Taniguchi

Integration of reinforcement learning and imitation learning is an important problem that has been studied for a long time in the field of intelligent robotics. Reinforcement learning optimizes policies to maximize the c…

General KnowledgeImitation Learningreinforcement-learningReinforcement Learning+1