PECOS: Prediction for Enormous and Correlated Output Spaces

TL;DR

PECOS is a modular machine learning framework designed to efficiently predict and rank relevant items from enormous, correlated output spaces, significantly improving real-time performance in large-scale applications.

Contribution

The paper introduces PECOS, a three-phase, versatile framework that organizes, narrows, and ranks large output spaces, enabling fast, real-time predictions for enormous, correlated label sets.

Findings

Achieves inference in less than 1 millisecond for 2.8 million labels.

Effectively handles long-tail items with limited training data.

Demonstrates versatility with plug-and-play components for different phases.

Abstract

Many large-scale applications amount to finding relevant results from an enormous output space of potential candidates. For example, finding the best matching product from a large catalog or suggesting related search phrases on a search engine. The size of the output space for these problems can range from millions to billions, and can even be infinite in some applications. Moreover, training data is often limited for the long-tail items in the output space. Fortunately, items in the output space are often correlated thereby presenting an opportunity to alleviate the data sparsity issue. In this paper, we propose the Prediction for Enormous and Correlated Output Spaces (PECOS) framework, a versatile and modular machine learning framework for solving prediction problems for very large output spaces, and apply it to the eXtreme Multilabel Ranking (XMR) problem: given an input instance, find and rank the most relevant items from an enormous but fixed and finite output space. We propose a three phase framework for PECOS: (i) in the first phase, PECOS organizes the output space using a semantic indexing scheme, (ii) in the second phase, PECOS uses the indexing to narrow down the output space by orders of magnitude using a machine learned matching scheme, and (iii) in the third phase, PECOS ranks the matched items using a final ranking scheme. The versatility and modularity of PECOS allows for easy plug-and-play of various choices for the indexing, matching, and ranking phases. We also develop very fast inference procedures which allow us to perform XMR predictions in real time; for example, inference takes less than 1 millisecond per input on the dataset with 2.8 million labels. The PECOS software is available at https://libpecos.org.