paper-with-me

홈 › Papers

Extreme Classification via Adversarial Softmax Approximation

2020-02-15 · ICLR 2020 1 · Robert Bamler, Stephan Mandt

Training a classifier over a large number of classes, known as 'extreme classification', has become a topic of major interest with applications in technology, science, and e-commerce. Traditional softmax regression induces a gradient cost proportional to the number of classes $C$, which often is prohibitively expensive. A popular scalable softmax approximation relies on uniform negative sampling, which suffers from slow convergence due a poor signal-to-noise ratio. In this paper, we propose a simple training method for drastically enhancing the gradient signal by drawing negative samples from an adversarial model that mimics the data distribution. Our contributions are three-fold: (i) an adversarial sampling mechanism that produces negative samples at a cost only logarithmic in $C$, thus still resulting in cheap gradient updates; (ii) a mathematical proof that this adversarial sampling minimizes the gradient variance while any bias due to non-uniform sampling can be removed; (iii) experimental results on large scale data sets that show a reduction of the training time by an order of magnitude relative to several competitive baselines.

📄 PDF Abstract BibTeX arXiv:2002.06298

Code (1)

mandt-lab/adversarial-negative-sampling 공식 구현 tf

Tasks

ClassificationGeneral Classification

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Similar Papers 제목 키워드 기반

Revisiting Softmax for Uncertainty Approximation in Text Classification

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Uncertainty approximation in text classification is an important area with applications in domain adaptation and interpretability. The most widely used uncertainty approximation method is Monte Carlo Dropout, which is co…

ClassificationDomain Adaptationtext-classificationText Classification

Revisiting Softmax for Uncertainty Approximation in Text Classification

2022-10-25 · Andreas Nugaard Holm, Dustin Wright, Isabelle Augenstein

Uncertainty approximation in text classification is an important area with applications in domain adaptation and interpretability. One of the most widely used uncertainty approximation methods is Monte Carlo (MC) Dropout…

ClassificationDomain Adaptationtext-classificationText Classification

Inverse classification with logistic and softmax classifiers: efficient optimization

2023-09-16 · Miguel Á. Carreira-Perpiñán, Suryabhan Singh Hada

In recent years, a certain type of problems have become of interest where one wants to query a trained classifier. Specifically, one wants to find the closest instance to a given input instance such that the classifier's…

counterfactualregression

Constraining Logits by Bounded Function for Adversarial Robustness

2020-10-06 · Sekitoshi Kanai, Masanori Yamada, Shin'ya Yamaguchi, Hiroshi Takahashi 외

We propose a method for improving adversarial robustness by addition of a new bounded function just before softmax. Recent studies hypothesize that small logits (inputs of softmax) by logit regularization can improve adv…

Adversarial Robustness

Adaptive Sampled Softmax with Inverted Multi-Index: Methods, Theory and Applications

2025-01-15 · Jin Chen, Jin Zhang, Xu Huang, Yi Yang 외

The softmax function is a cornerstone of multi-class classification, integral to a wide range of machine learning applications, from large-scale retrieval and ranking models to advanced large language models. However, it…

Multi-class Classification