PARK: Personalized academic retrieval with knowledge-graphs

2025-07-18

AI Summary

To address information overload in academic search—stemming from inadequate user interest modeling and underutilization of citation graphs—this paper proposes a knowledge graph–enhanced two-stage personalized retrieval method. First, the academic citation graph is structured into a heterogeneous knowledge graph integrating author publication histories and paper semantics. Second, Translational Embedding (TransE) aligns this graph with language models in a shared semantic space, and the resulting representations are jointly optimized within a neural retrieval framework in an end-to-end manner. This work is the first to systematically integrate structured knowledge graphs, translation-based embedding, and neural retrieval, enabling both explicit relational modeling and implicit interest discovery. Evaluated on four major academic search benchmarks across three retrieval tasks, the method achieves up to a 10% improvement in MAP@100 over state-of-the-art baselines, significantly outperforming conventional graph-based and personalized retrieval approaches.

Technology Category

• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Search and Optimization: Learning to Search
• Machine Learning: Graph-based Machine Learning

Application Category

• Graph Algorithms and Modeling for the Web: Querying, indexing, and retrieval in Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding

Abstract

Academic Search is a search task aimed to manage and retrieve scientific documents like journal articles and conference papers. Personalization in this context meets individual researchers' needs by leveraging, through user profiles, the user related information (e.g. documents authored by a researcher), to improve search effectiveness and to reduce the information overload. While citation graphs are a valuable means to support the outcome of recommender systems, their use in personalized academic search (with, e.g. nodes as papers and edges as citations) is still under-explored. Existing personalized models for academic search often struggle to fully capture users' academic interests. To address this, we propose a two-step approach: first, training a neural language model for retrieval, then converting the academic graph into a knowledge graph and embedding it into a shared semantic space with the language model using translational embedding techniques. This allows user models to capture both explicit relationships and hidden structures in citation graphs and paper content. We evaluate our approach in four academic search domains, outperforming traditional graph-based and personalized models in three out of four, with up to a 10% improvement in MAP@100 over the second-best model. This highlights the potential of knowledge graph-based user models to enhance retrieval effectiveness.

Problem

• Enhancing academic search with personalized knowledge graphs
• Improving retrieval by integrating citation graph embeddings
• Addressing information overload in scientific document retrieval

Innovation

• Neural language model for academic retrieval
• Knowledge graph embedding with translational techniques
• Shared semantic space for user models