Relational retrieval using a combination of path-constrained random walks

By Ni Lao, William W. Cohen. Machine-mediated learning, 2010

668 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/054ba27fe5cc6085d20ea2707de886db6865dbed

How researchers see this paper

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

In Artificial Intelligence

Citations in the corpus

Relational Representation Learning for Dynamic (Knowledge) Graphs: A Survey (2019, neutral): “Examples of such approaches include [131, 132, 52].”
Incorporating Relation Paths in Neural Relation Extraction (2016, methodology): “We integrate the information from both direct sentences and relation paths, then predict the conﬁdence of each relation.”
Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction (2021, methodology): “In traditional methods, such a local structure is encoded by counting different types of random walks from u to v [35, 15].”
Compositional Learning of Embeddings for Relation Paths in Knowledge Base and Text (2016, background): “Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, pages 1434–1444, Berlin, Germany, August 7-12, 2016. c©2016 Association for Computational Linguistics”
Structured Embedding via Pairwise Relations and Long-Range Interactions in Knowledge Base (2015, methodology): “Given a set of pairs of entities that are directly pairwise relation R, Path Ranking Algorithm (PRA) (Lao, Mitchell, and Cohen 2011; Lao and Cohen 2010b) then performs a random walk on the knowledge graph to identify the long-range paths starting at all the source entities (nodes).”
Constructing Datasets for Multi-hop Reading Comprehension Across Documents (2017, background): “though efforts to circumvent sparsity have been undertaken (Schoenmackers et al., 2008; Schoenmackers et al., 2010). A more scalable approach to composite rule learning is the Path Ranking Algorithm (Lao and Cohen, 2010; Lao et al., 2011), which performs random walks to identify salient paths betwee”
Graph Learning: A Survey (2021, background): “The central problem of relational inference is inferring unknown knowledge from the existing facts in knowledge bases [103].”
Knowledge Graphs (2020, neutral): “Supervised approaches rather extract features for input edges from external knowledge graphs [308, 509, 577] and use these features to train a classification model to label the edges as true or false.”
ProjE: Embedding Projection for Knowledge Graph Completion (2016, background): “4 show that ProjE outperforms existing fact checking and link prediction models [2, 6, 17, 9, 15, 22] in all but one question type.”
Neural, symbolic and neural-symbolic reasoning on knowledge graphs (2021, methodology): “Path-Ranking Algorithm (PRA) (Lao and Cohen, 2010) is a state-of-the-art path-based method.”
Neural Approaches to Conversational AI (2018, positive): “ree categories of multi-step KBR methods. They differ in whether reasoning is performed in a discrete symbolic space or a continuous neural space. 3.4.1 Symbolic Methods Path Ranking Algorithm (PRA) (Lao and Cohen, 2010; Lao et al., 2011) is one of the primary symbolic approaches to learning relatio”
Research-paper recommender systems: a literature survey (2015, methodology): “Depending on the entities in the graph, connections can be citations [10], [79], [84], purchases [57], “published in” relations, [10], [79], [127], authorship [4], [10], [127], relatedness between genes(29) [4], or occurrences of genes in papers [79].”
A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multi-Modal (2022, background): “Path-Ranking Algorithm (PRA) [145] derives the path-based logic rules under path constraints.”
Differentiable Learning of Logical Rules for Knowledge Base Reasoning (2017, methodology): “Many past learning systems have thus used optimization methods that interleave moves in a discrete structure space with moves in parameter space [12, 13, 14, 27].”
Knowledge Graph Completion: A Review (2020, methodology): “Path Ranking Algorithm (PRA) [40] is one of the earlier graph completion methods based on graphs.”
Link Prediction Based on Graph Neural Networks (2018, methodology): “We omit path ranking methods [28] as well as other recent methods which are specifically designed for knowledge graphs or recommender systems [23, 35].”