Leveraging semantically similar queries for ranking via combining representations

TL;DR

This paper explores how combining multiple representations and leveraging semantically similar queries can improve ranking performance, especially in data-scarce scenarios, demonstrated through simulations and real-world datasets.

Contribution

It introduces a method to utilize semantically similar queries for ranking, addressing data scarcity issues by combining representations and sharing information across queries.

Findings

Using similar queries improves ranking accuracy in data-scarce settings

Combining multiple representations enhances ranking performance

Application to Bing navigational graph and Drosophila connectome shows effectiveness

Abstract

In modern ranking problems, different and disparate representations of the items to be ranked are often available. It is sensible, then, to try to combine these representations to improve ranking. Indeed, learning to rank via combining representations is both principled and practical for learning a ranking function for a particular query. In extremely data-scarce settings, however, the amount of labeled data available for a particular query can lead to a highly variable and ineffective ranking function. One way to mitigate the effect of the small amount of data is to leverage information from semantically similar queries. Indeed, as we demonstrate in simulation settings and real data examples, when semantically similar queries are available it is possible to gainfully use them when ranking with respect to a particular query. We describe and explore this phenomenon in the context of the bias-variance trade off and apply it to the data-scarce settings of a Bing navigational graph and the Drosophila larva connectome.