中文
相关论文

相关论文: Neural-Symbolic Logic Query Answering in Non-Eucli…

200 篇论文

Bridging continuous perceptual signals and discrete symbolic reasoning is a fundamental challenge in AI systems that must operate under uncertainty. We present a neuro-symbolic framework that explicitly models and propagates uncertainty…

人工智能 · 计算机科学 2025-11-19 Jiahao Wu , Shengwen Yu

Answering complex queries over knowledge graphs (KG) is an important yet challenging task because of the KG incompleteness issue and cascading errors during reasoning. Recent query embedding (QE) approaches to embed the entities and…

人工智能 · 计算机科学 2022-09-20 Zezhong Xu , Wen Zhang , Peng Ye , Hui Chen , Huajun Chen

Recent advances in the integration of deep learning with automated theorem proving have centered around the representation of logical formulae as inputs to deep learning systems. In particular, there has been a growing interest in adapting…

The dominant neural architectures in question answer retrieval are based on recurrent or convolutional encoders configured with complex word matching layers. Given that recent architectural innovations are mostly new word interaction layers…

信息检索 · 计算机科学 2017-11-27 Yi Tay , Luu Anh Tuan , Siu Cheung Hui

Temporal knowledge graph (TKG) reasoning predicts future events based on historical data, but it's challenging due to the complex semantic and hierarchical information involved. Existing Euclidean models excel at capturing semantics but…

机器学习 · 计算机科学 2024-09-04 Siling Feng , Zhisheng Qi , Cong Lin

Graph representation learning in Euclidean space, despite its widespread adoption and proven utility in many domains, often struggles to effectively capture the inherent hierarchical and complex relational structures prevalent in real-world…

机器学习 · 计算机科学 2025-08-26 Menglin Yang , Min Zhou , Tong Zhang , Jiahong Liu , Zhihao Li , Lujia Pan , Hui Xiong , Irwin King

Most previous heterogeneous graph embedding models represent elements in a heterogeneous graph as vector representations in a low-dimensional Euclidean space. However, because heterogeneous graphs inherently possess complex structures, such…

机器学习 · 计算机科学 2024-04-16 Jongmin Park , Seunghoon Han , Soohwan Jeong , Sungsu Lim

Recent papers in the graph machine learning literature have introduced a number of approaches for hyperbolic representation learning. The asserted benefits are improved performance on a variety of graph tasks, node classification and link…

机器学习 · 计算机科学 2025-02-26 Isay Katsman , Anna Gilbert

Recent work on recommender systems has considered external knowledge graphs as valuable sources of information, not only to produce better recommendations but also to provide explanations of why the recommended items were chosen. Pure…

信息检索 · 计算机科学 2020-07-28 Yikun Xian , Zuohui Fu , Qiaoying Huang , S. Muthukrishnan , Yongfeng Zhang

Formulating and answering logical queries is a standard communication interface for knowledge graphs (KGs). Alleviating the notorious incompleteness of real-world KGs, neural methods achieved impressive results in link prediction and…

人工智能 · 计算机科学 2022-11-10 Mikhail Galkin , Zhaocheng Zhu , Hongyu Ren , Jian Tang

This chapter delves into the emerging field of neuro-symbolic query optimization for knowledge graphs (KGs), presenting a comprehensive exploration of how neural and symbolic techniques can be integrated to enhance query processing.…

数据库 · 计算机科学 2024-11-22 Maribel Acosta , Chang Qin , Tim Schwabe

Developing models that can learn to reason is a notoriously challenging problem. We focus on reasoning in relational domains, where the use of Graph Neural Networks (GNNs) seems like a natural choice. However, previous work has shown that…

人工智能 · 计算机科学 2025-03-03 Irtaza Khalid , Steven Schockaert

Multi-step reasoning remains a central challenge for large language models: single-pass generation is efficient but lacks accuracy; tree-search methods explore multiple paths but are computation-heavy. We address this gap by distilling…

人工智能 · 计算机科学 2026-05-29 Yuyu Liu , Haotian Xu , Yanan He , Sarang Rajendra Patil , Mengjia Xu , Tengfei Ma

Functional magnetic resonance imaging (fMRI) reveals complex brain functional networks with hierarchical topologies crucial for cognitive processing. Standard Euclidean Graph Neural Networks (GNNs) often struggle to represent these…

计算机视觉与模式识别 · 计算机科学 2026-03-03 Junhao Jia , Yunyou Liu , Cheng Yang , Yifei Sun , Feiwei Qin , Changmiao Wang , Yong Peng

Our goal is a modern approach to answering questions via systematic reasoning where answers are supported by human interpretable proof trees grounded in an NL corpus of authoritative facts. Such a system would help alleviate the challenges…

计算与语言 · 计算机科学 2024-08-14 Nathaniel Weir , Peter Clark , Benjamin Van Durme

We marry two powerful ideas: deep representation learning for visual recognition and language understanding, and symbolic program execution for reasoning. Our neural-symbolic visual question answering (NS-VQA) system first recovers a…

人工智能 · 计算机科学 2019-01-16 Kexin Yi , Jiajun Wu , Chuang Gan , Antonio Torralba , Pushmeet Kohli , Joshua B. Tenenbaum

Similarly to other connectionist models, Graph Neural Networks (GNNs) lack transparency in their decision-making. A number of sub-symbolic approaches have been developed to provide insights into the GNN decision making process. These are…

人工智能 · 计算机科学 2021-12-06 Anna Himmelhuber , Stephan Grimm , Sonja Zillner , Mitchell Joblin , Martin Ringsquandl , Thomas Runkler

Knowledge graphs are an expressive and widely used data structure due to their ability to integrate data from different domains in a sensible and machine-readable way. Thus, they can be used to model a variety of systems such as molecules…

神经与进化计算 · 计算机科学 2023-08-28 Dominik Dold , Josep Soler Garrido , Victor Caceres Chian , Marcel Hildebrandt , Thomas Runkler

Real-world visual data exhibit intrinsic hierarchical structures that can be represented effectively in hyperbolic spaces. Hyperbolic neural networks (HNNs) are a promising approach for learning feature representations in such spaces.…

计算机视觉与模式识别 · 计算机科学 2024-02-08 Ahmad Bdeir , Kristian Schwethelm , Niels Landwehr

Foundation models pre-trained on massive datasets, including large language models (LLMs), vision-language models (VLMs), and large multimodal models, have demonstrated remarkable success in diverse downstream tasks. However, recent studies…

机器学习 · 计算机科学 2025-07-25 Neil He , Hiren Madhu , Ngoc Bui , Menglin Yang , Rex Ying