Random Walk Inference and Learning in A Large Scale Knowledge Base

By Ni Lao, Tom Michael Mitchell, William W. Cohen. 2011

668 citations recorded by the source corpus.

Subfields: Information Retrieval & Search, Graph Learning

How researchers see this paper

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

In Information Retrieval & Search

In Graph Learning

Citations in the corpus

Semantic Parsing on Freebase from Question-Answer Pairs (2013, background): “An interesting midpoint involves keeping the structured knowledge base but augmenting the predicates, for example using random walks (Lao et al., 2011) or Markov logic (Zhang et al.”
Constructing Datasets for Multi-hop Reading Comprehension Across Documents (2017, background): “A more scalable approach to composite rule learning is the Path Ranking Algorithm (PRA) (Lao and Cohen, 2010; Lao et al., 2011), which performs random walks to identify salient paths between entities.”
Neural Approaches to Conversational AI (2018, positive): “For each relation, its top-2 PRA paths are presented, adapted from Lao et al. (2011).”
Neural Symbolic Machines: Learning Semantic Parsers on Freebase with Weak Supervision (2016, methodology): “NSM is similar to the Path Ranking Algorithm (PRA) (Lao et al., 2011) in that semantics is encoded as a sequence of actions, and denotations are used to prune the search space during learning.”
The More You Know: Using Knowledge Graphs for Image Classification (2016, background): “Approaches such as [17] use random walks on the graphs to learn patterns of edges while performing the walk and predict new edges in the knowledge graph.”
End-to-end Differentiable Proving (2017, background): “In addition, NTPs are related to random walk [48, 49, 11, 12] and path encoding models [14, 16].”
TabFact: A Large-scale Dataset for Table-based Fact Verification (2019, background): “NSM is modified from Liang et al. (2017). NSM We follow Liang et al.”
Embedding Entities and Relations for Learning and Inference in Knowledge Bases (2014, background): “(SRL) (Getoor & Taskar, 2007), such as Markov-logic networks (Richardson & Domingos, 2006), which directly encode multi-relational graphs using probabilistic models; (2) path ranking methods (Lao et al., 2011; Dong et al., 2014), which explicitly explore the large feature space of relations ”
Commonsense Knowledge Base Completion (2016, methodology): “Our methods are similar to past work on KBC (Mintz et al., 2009; Nickel et al., 2011; Lao et al., 2011; Nickel et al., 2012; Riedel et al., 2013; Gardner et al., 2014; West et al., 2014), particularly methods based on distributed representations and neural networks (Socher et al., 2013; Bordes et…”
Representing Text for Joint Embedding of Text and Knowledge Bases (2015, background): “…et al. (2015) provide a broad overview of machine learning models for knowledge graphs, including models based on observed graph features such as the path ranking algorithm (Lao et al., 2011), models based on continuous representations (latent features), and model combinations (Dong et al., 2014).”
Traversing Knowledge Graphs in Vector Space (2015, background): “Paths in a knowledge graph have proven to be important features for predicting the existence of single edges (Lao et al., 2011).”
Automated Fact Checking: Task Formulations, Methods and Future Directions (2018, methodology): “Ciampaglia et al. (2015) use network analysis to predict whether an unobserved triple is likely to appear in a graph by modeling the task as a path ranking problem (Lao et al., 2011).”
Visual Semantic Reasoning for Image-Text Matching (2019, methodology): “More recent methods, such as path ranking algorithm [22], perform reasoning on structured knowledge bases by taking use of statistical learning to extract effective patterns.”
Quaternion Knowledge Graph Embeddings (2019, background): “Composition patterns are commonplace in knowledge graphs [Lao et al., 2011, Neelakantan et al., 2015].”
Canonical Tensor Decomposition for Knowledge Base Completion (2018, background): “While some approaches explicitly use the graph structure during inference (Lao et al., 2011), we focus here on representation learning and tensor factorization methods, which are the state-of-the-art on the benchmark datasets we use.”
RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space (2018, background): “There are also a large body of relational approaches for modeling the relational patterns on knowledge graphs (Lao et al., 2011; Neelakantan et al., 2015; Das et al., 2016; Rockt ¨ aschel & Riedel, 2017; Yang et al., 2017).”
Learning to Refine an Automatically Extracted Knowledge Base Using Markov Logic (2012, neutral): “[24] proposed an approach to learn chain rules in NELL such as “If an athlete x plays for a team y, and team y plays”
Computational Fact Checking from Knowledge Networks (2015, methodology): “This approach is also related to the Path Ranking Algorithm [30], except that here we use the shortest path (equivalent to maximum probability) rather than combining a sample of bounded-length paths in a learning framework.”