Item Tagging for Information Retrieval: A Tripartite Graph Neural Network based Approach

TL;DR

This paper introduces TagGNN, a tripartite graph neural network model that improves item tagging for information retrieval by leveraging query logs and a unified link prediction framework, outperforming existing methods.

Contribution

The paper proposes a novel tripartite graph neural network approach for item tagging in IR, integrating query logs and optimizing full and partial tag prediction in a unified model.

Findings

TagGNN outperforms state-of-the-art multi-label classification methods.

Utilizes query logs to enrich item representations.

Effective on both open and industrial datasets.

Abstract

Tagging has been recognized as a successful practice to boost relevance matching for information retrieval (IR), especially when items lack rich textual descriptions. A lot of research has been done for either multi-label text categorization or image annotation. However, there is a lack of published work that targets at item tagging specifically for IR. Directly applying a traditional multi-label classification model for item tagging is sub-optimal, due to the ignorance of unique characteristics in IR. In this work, we propose to formulate item tagging as a link prediction problem between item nodes and tag nodes. To enrich the representation of items, we leverage the query logs available in IR tasks, and construct a query-item-tag tripartite graph. This formulation results in a TagGNN model that utilizes heterogeneous graph neural networks with multiple types of nodes and edges. Different from previous research, we also optimize both full tag prediction and partial tag completion cases in a unified framework via a primary-dual loss mechanism. Experimental results on both open and industrial datasets show that our TagGNN approach outperforms the state-of-the-art multi-label classification approaches.