Document Network Embedding: Coping For Missing Content And Missing Links

Abstract

Searching through networks of documents is an important task. A promising path to improve the performance of information retrieval systems in this context is to leverage dense node and content representations learned with embedding techniques. However, these techniques cannot learn representations for documents that are either isolated or whose content is missing. To tackle this issue, assuming that the topology of the network and the content of the documents correlate, we propose to estimate the missing node representations from the available content representations, and conversely. Inspired by recent advances in machine translation, we detail in this paper how to learn a linear transformation from a set of aligned content and node representations. The projection matrix is efficiently calculated in terms of the singular value decomposition. The usefulness of the proposed method is highlighted by the improved ability to predict the neighborhood of nodes whose links are unobserved based

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keydupuy2019document

Related papers

• Search Efficient Binary Network Embedding (2019)3.58
• Structure And Semantics Preserving Document Representations (2022)3.58
• Improving Document Representations By Generating Pseudo Query Embeddings For Dense Retrieval (2021)9.41
• VERSE: Versatile Graph Embeddings From Similarity Measures (2018)17.42
• Utilizing Embeddings For Ad-hoc Retrieval By Document-to-document Similarity (2017)0.00
• Joint Embedding Of Meta-path And Meta-graph For Heterogeneous Information Networks (2018)10.61
• Meta-path Guided Embedding For Similarity Search In Large-scale Heterogeneous Information Networks (2016)0.00
• QUINT: Node Embedding Using Network Hashing (2021)5.24