Layered Graph Embedding for Entity Recommendation using Wikipedia in the Yahoo! Knowledge Graph

@article{Ni2020LayeredGE,
  title={Layered Graph Embedding for Entity Recommendation using Wikipedia in the Yahoo! Knowledge Graph},
  author={Chien-Chun Ni and Kin Sum Liu and Nicolas Torzec},
  journal={Companion Proceedings of the Web Conference 2020},
  year={2020}
}
In this paper, we describe an embedding-based entity recommendation framework for Wikipedia that organizes Wikipedia into a collection of graphs layered on top of each others, learns complementary entity representations from their topology and content, and combines them with a lightweight learning-to-rank approach to recommend related entities on Wikipedia. Through offline and online evaluations, we show that the resulting embeddings and recommendations perform well in terms of quality and user… 

Figures and Tables from this paper

Competitor Mining from Web Encyclopedia: A Graph Embedding Approach

TLDR
This paper proposes to mine competitors based on the similarity among graph nodes and further presents a similarity computation method combing graph-node similarity and textual relevance and compares the proposed method with four existing algorithms on the real data sets crawled from Wikipedia and DBpedia.

Multi-level Recommendation Reasoning over Knowledge Graphs with Reinforcement Learning

TLDR
A reinforcement learning framework for multi-level recommendation reasoning over KGs is proposed, which leverages both ontology-view and instance-view KGs to model multi- level user interests and automatically selects between high-level concepts and low-level ones to form reasoning paths that better reveal user interests.

OEKG: The Open Event Knowledge Graph

TLDR
This paper presents the Open Event Knowledge Graph (OEKG), a multilingual, event-centric, temporal knowledge graph composed of seven different data sets from multiple application domains, including question answering, entity recommendation and named entity recognition.

Semantics-Aware Shilling Attacks against collaborative recommender systems via Knowledge Graphs

TLDR
Experimental results indicate the benefit of embracing KGs in favor of the attackers’ capability in attacking recommendation systems, and introduce a new attack strategy, named semantics-aware shilling attack (SAShA), that leverages semantic features extracted from a knowledge graph.

Fourth Knowledge-aware and Conversational Recommender Systems Workshop (KaRS)

TLDR
Although very effective in predicting relevant items, collaborative approaches miss some very interesting features that go beyond the accuracy of results and move in the direction of providing novel and diverse results as well as generating explanations for recommended items.

Third Knowledge-aware and Conversational Recommender Systems Workshop (KaRS)

TLDR
Although very effective in predicting relevant items, collaborative approaches miss some very interesting features that go beyond the accuracy of results and move in the direction of providing novel and diverse results as well as generating an explanation for the recommended items.

WikiContradiction: Detecting Self-Contradiction Articles on Wikipedia

TLDR
The first model, Pairwise Contradiction Neural Network (PCNN), is presented, to not only effectively identify self-contradiction articles, but also highlight the most contradiction pairs of contradiction sentences.

User Access Models to Event-Centric Information

TLDR
This PhD research aims to develop efficient and effective user access models to event-centric information by leveraging well-structured information in Knowledge Graphs to tackle the challenges researchers encounter during their research in a workflow.

References

SHOWING 1-10 OF 27 REFERENCES

Leveraging Wikipedia Knowledge for Entity Recommendations

TLDR
Wikipedia-based Features for Entity Recommendation (WiFER) is presented that combines different features extracted from Wikipedia in order to provide related entity recommendations.

Multi-Layered Network Embedding

TLDR
A principled framework MANE is proposed to model both within-layer connections and cross-layer network dependencies simultaneously in a unified optimization framework for embedding representation learning and experiments on real-world multi-layered networks corroborate the effectiveness of the proposed framework.

Entity Recommendations in Web Search

TLDR
Spark is described, a recommendation engine that links a user's initial query to an entity within a knowledge base and provides a ranking of the related entities and is currently powering Yahoo! Web Search result pages.

Document Embedding with Paragraph Vectors

TLDR
This work observes that the Paragraph Vector method performs significantly better than other methods, and proposes a simple improvement to enhance embedding quality, and shows that much like word embeddings, vector operations on Paragraph Vectors can perform useful semantic results.

Learning to Recommend Related Entities to Search Users

TLDR
This work proposes a probabilistic Three-way Entity Model (TEM) that provides personalized recommendation of related entities using three data sources: knowledge base, search click log, and entity pane log and provides an inference technique to learn the parameters in TEM.

On building entity recommender systems using user click log and freebase knowledge

TLDR
This paper proposes a generic, robust, and time-aware personalized recommendation framework to utilize heuristics and features of the datasets and demonstrates the effectiveness of the proposed framework over other popular and state-of-the-art recommendation techniques.

A Comprehensive Survey of Graph Embedding: Problems, Techniques, and Applications

TLDR
This survey conducts a comprehensive review of the literature in graph embedding and proposes two taxonomies ofGraph embedding which correspond to what challenges exist in differentgraph embedding problem settings and how the existing work addresses these challenges in their solutions.

Improved Deep Embeddings for Inferencing with Multi-Layered Networks

TLDR
This paper proposes a novel approach that first obtains node embeddings in all layers jointly via DeepWalk on asupra graph, which allows interactions between layers, and then fine-tunes theembeddings to encourage cohesive structure in the latent space.

DeepWalk: online learning of social representations

TLDR
DeepWalk is an online learning algorithm which builds useful incremental results, and is trivially parallelizable, which make it suitable for a broad class of real world applications such as network classification, and anomaly detection.

node2vec: Scalable Feature Learning for Networks

TLDR
In node2vec, an algorithmic framework for learning continuous feature representations for nodes in networks, a flexible notion of a node's network neighborhood is defined and a biased random walk procedure is designed, which efficiently explores diverse neighborhoods.