Leveraging Order-Free Tag Relations for Context-Aware Recommendation

TL;DR

This paper introduces a novel sequence-oblivious method for tag recommendation that effectively captures inter-dependencies among tags without relying on their order, outperforming previous approaches in real-world datasets.

Contribution

The paper proposes a new order-free generation approach for tag recommendation that addresses the limitations of existing ranking and autoregressive methods.

Findings

Significantly outperforms previous methods on Instagram and Stack Overflow datasets.

Effectively models inter-dependencies among tags without considering their order.

Demonstrates robustness across different domains.

Abstract

Tag recommendation relies on either a ranking function for top-$k$ tags or an autoregressive generation method. However, the previous methods neglect one of two seemingly conflicting yet desirable characteristics of a tag set: orderlessness and inter-dependency. While the ranking approach fails to address the inter-dependency among tags when they are ranked, the autoregressive approach fails to take orderlessness into account because it is designed to utilize sequential relations among tokens. We propose a sequence-oblivious generation method for tag recommendation, in which the next tag to be generated is independent of the order of the generated tags and the order of the ground truth tags occurring in training data. Empirical results on two different domains, Instagram and Stack Overflow, show that our method is significantly superior to the previous approaches.