Differentiable Learning of Logical Rules for Knowledge Base Reasoning

By Fan Yang, Zhilin Yang, William W. Cohen. 2017

763 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

Citations in the corpus

Multi-step Retriever-Reader Interaction for Scalable Open-domain Question Answering (2019, background): “, 2016) for question answering in text and knowledge bases (Das et al., 2017; Yang et al., 2017; Das et al., 2018).”
RuleBERT: Teaching Soft Rules to Pre-Trained Language Models (2021, methodology): “Unlike previous work (Hamilton et al., 2018; Yang et al., 2017; Minervini et al., 2020), we do not design a new, ad-hoc module for neural reasoning, but we rely solely on the transformer’s capability to emulate algorithms (Wang et al., 2019b; Lample and Charton, 2020).”
Neural Logic Machines (2019, background): “Our work is also related to symbolic relational reasoning, which has a wide application in processing discrete data structures such as knowledge graphs and social graphs (Zhu et al., 2014; Kipf & Welling, 2017; Zeng et al., 2017; Yang et al., 2017).”
Neural-Symbolic Computing: An Effective Methodology for Principled Integration of Machine Learning and Reasoning (2019, background): “For example, in Neural Logic Programming (NLP) [57], learning of rules are based on the differentiable inference of TensorLog [6].”
Learning to Exploit Long-term Relational Dependencies in Knowledge Graphs (2019, methodology): “There are many similar methods that purely leverage relational paths or employ chunk-based paths (Guu et al., 2015; McCallum et al., 2017; Yang et al., 2017).”
Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning (2017, methodology): “We also compare MINERVA to NeuralLP [48] on the UMLS and KINSHIP datasets.”
Neural, symbolic and neural-symbolic reasoning on knowledge graphs (2021, methodology): “Neural-Num-LP (Wang et al., 2020) extends Neural LP (Yang et al., 2017) to learn the numerical rules.”
Logical Rule Induction and Theory Learning Using Neural Theorem Proving (2018, background): “In Neural LP (Yang, Yang, and Cohen 2017), the system can learn chaining-type rules.”
A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multi-Modal (2022, methodology): “Besides, NeuralLP [8] leverages attention mechanisms and auxiliary memory to optimize the gradients for mining the rules, and Neural-Num-LP [108] further integrates the cumulative sum operations and dynamic programming with NeuralLP to learn numerical rules.”
Bootstrapping Entity Alignment with Knowledge Graph Embedding (2018, methodology): “Bootstrapping is a widely-used semi-supervised learning technique [Yarowsky, 1995; Abney, 2004].”
Neurosymbolic AI: the 3rd wave (2020, background): “Related work seeking to explore the advantages of distributed representations of logic include (Yang et al. 2017), which is based on stochastic logic programs, (Evans and Grefenstette 2018), with a focus on inductive programming, and Minervini et al.”
Prototypical Representation Learning for Relation Extraction (2021, methodology): “…methods reason relations via symbolic logic rules, with adopting probabilistic graphical models or inductive logic systems to learn and infer logic rules orienting to relations (Cohen & Hirsh, 1994; Wang et al., 2015; Yang et al., 2017; Chen et al., 2018; Kazemi & Poole, 2018; Qu & Tang, 2019).”
Inductive Relation Prediction by Subgraph Reasoning (2019, methodology): “Building on NeuralLP, Sadeghian et al. (2019) recently proposed DRUM, which learns more accurate rules.”
RelNN: A Deep Neural Model for Relational Learning (2017, background): “Examples of these works include path-constrained random walks (e.g., (Lao and Cohen 2010; Lao, Mitchell, and Cohen 2011)), and several hybrid approaches (e.g., (Das et al. 2017; Rockt¨aschel and Riedel 2017; Yang, Yang, and Cohen 2017; Wang, Shi, and Yeung 2017)).”
Knowledge Graphs (2020, neutral): “Along these lines, NeuralLP [568] uses an attention mechanism to select a variable-length sequence of edge labels for path-like rules of the form ?x ?y1 p1 .”
Adaptive Convolution for Multi-Relational Learning (2019, background): “• Methods that further introduce multi-layer structures and non-linearity, in particular those based on neural networks, including R-GCN (Schlichtkrull et al., 2017a), Neural LP (Yang et al., 2017), ConvE (Dettmers et al., 2018), and ConvKB (Nguyen et al., 2018).”
SATNet: Bridging deep learning and logical reasoning using a differentiable satisfiability solver (2019, background): “…focused on creating differentiable modules from an existing set of known relationships , so that a deep network can learn the parameters of these relationships (Dai et al., 2018; Manhaeve et al., 2018; Sourek et al., 2018; Xu et al., 2018; Hu et al., 2016; Yang et al., 2017; Selsam et al., 2018).”