SoDeep: a Sorting Deep net to learn ranking loss surrogates

04/08/2019
by   Martin Engilberge, et al.
0

Several tasks in machine learning are evaluated using non-differentiable metrics such as mean average precision or Spearman correlation. However, their non-differentiability prevents from using them as objective functions in a learning framework. Surrogate and relaxation methods exist but tend to be specific to a given metric. In the present work, we introduce a new method to learn approximations of such non-differentiable objective functions. Our approach is based on a deep architecture that approximates the sorting of arbitrary sets of scores. It is trained virtually for free using synthetic data. This sorting deep (SoDeep) net can then be combined in a plug-and-play manner with existing deep architectures. We demonstrate the interest of our approach in three different tasks that require ranking: Cross-modal text-image retrieval, multi-label image classification and visual memorability ranking. Our approach yields very competitive results on these three tasks, which validates the merit and the flexibility of SoDeep as a proxy for sorting operation in ranking-based losses.

READ FULL TEXT
research
02/15/2021

NeuralNDCG: Direct Optimisation of a Ranking Metric via Differentiable Relaxation of Sorting

Learning to Rank (LTR) algorithms are usually evaluated using Informatio...
research
12/12/2020

PiRank: Learning To Rank via Differentiable Sorting

A key challenge with machine learning approaches for ranking is the gap ...
research
03/17/2022

Monotonic Differentiable Sorting Networks

Differentiable sorting algorithms allow training with sorting and rankin...
research
12/02/2019

AP-Perf: Incorporating Generic Performance Metrics in Differentiable Learning

We propose a method that enables practitioners to conveniently incorpora...
research
02/20/2020

Fast Differentiable Sorting and Ranking

The sorting operation is one of the most basic and commonly used buildin...
research
02/15/2018

Black Hole Metric: Overcoming the PageRank Normalization Problem

In network science, there is often the need to sort the graph nodes. Whi...
research
05/09/2022

Improved Evaluation and Generation of Grid Layouts using Distance Preservation Quality and Linear Assignment Sorting

Images sorted by similarity enables more images to be viewed simultaneou...

Please sign up or login with your details

Forgot password? Click here to reset