Towards Probabilistic Inductive Logic Programming with Neurosymbolic Inference and Relaxation

원문 초록

Many inductive logic programming (ILP) methods are incapable of learning programs from probabilistic background knowledge, e.g. coming from sensory data or neural networks with probabilities. We propose Propper, which handles flawed and probabilistic background knowledge by extending ILP with a combination of neurosymbolic inference, a continuous criterion for hypothesis selection (BCE) and a relaxation of the hypothesis constrainer (NoisyCombo). For relational patterns in noisy images, Propper can learn programs from as few as 8 examples. It outperforms binary ILP and statistical models such as a Graph Neural Network.

함께 살펴볼 논문

공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.

arXiv:2507.15205공통 태그 Graph Neural Network공식 코드 · Papers with Code 등록 2025-07-21

Long-Short Distance Graph Neural Networks and Improved Curriculum Learning for Emotion Recognition in Conversation

arXiv:2507.03947공통 태그 Graph Neural Network공식 코드 · Papers with Code 등록 2025-07-05

Graph Collaborative Attention Network for Link Prediction in Knowledge Graphs

arXiv:2507.02690공통 태그 Graph Neural Network공식 코드 · Papers with Code 등록 2025-07-03

RLHGNN: Reinforcement Learning-driven Heterogeneous Graph Neural Network for Next Activity Prediction in Business Processes

arXiv:2506.17064공통 태그 Graph Neural Network공식 코드 · Papers with Code 등록 2025-06-20

토론

이 논문과 연결된 포럼 글이 아직 없습니다.

포럼에서 토론 찾기