Effective Personalized Search With Heterogeneous Graph Based Hawkes Process
- 13 May 2024
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Big Data
- Vol. 11 (2) , 402-413
Abstract
Personalized search aims at re-ranking search results with reference to users’ background information. The state-of-the-art personalized search methods often consider both the short-term search interests from current session behaviors and the long-term search interests from previous session behaviors. However, sessions in real-world search scenarios are usually very short, and a large number of sessions contain only one query, which makes it difficult to model short-term search interests. Intuitively, apart from current session behaviors, some recent historical session behaviors could also contribute to the current search interests, and the influence of these behaviors typically decays over time. Based on this intuition, we propose a novel heterogeneous graph based Hawkes process to improve the effectiveness of personalized search. Specifically, we first construct a heterogeneous graph to model multiple relations between users, queries, and documents. Then, we propose a heterogeneous graph neural network based algorithm to encode the representations of users’ historical search behaviors. After that, we develop a multivariate Hawkes process to capture the influence of historical search behaviors on the current search intent. Our approach can dynamically model the influence of historical behaviors in a continuous time space. Thus, both the current session behaviors and the historical session behaviors can be utilized to characterize a more accurate current search intent. We evaluate our method using three real-life datasets, and the results show that our approach significantly outperforms the state-of-the-art methods in terms of several widely-used precision metrics.Keywords
Funding Information
- National Key Research and Development Program of China (2021YFB3301301)
- National Natural Science Foundation of China (U2241211, 62072034)
This publication has 39 references indexed in Scilit:
- Enhancing Potential Re-Finding in Personalized Search With Hierarchical Memory NetworksIEEE Transactions on Knowledge and Data Engineering, 2021
- Dynamic Heterogeneous Graph Embedding via Heterogeneous Hawkes Process2021
- Looking Back on the Past: Active Learning With Historical Evaluation ResultsIEEE Transactions on Knowledge and Data Engineering, 2020
- Temporal Latent Topic User Profiles for Search Personalisation2015
- Towards query log based personalization using topic models2010
- Classification-enhanced ranking2010
- Web search personalization with ontological user profiles2007
- A large-scale evaluation and analysis of personalized search strategies2007
- Learning to rank using gradient descent2005
- Spectra of some self-exciting and mutually exciting point processesBiometrika, 1971