paper-with-me

홈 › Papers

Relaxed Softmax for learning from Positive and Unlabeled data

2019-09-17 · Ugo Tanielian, Flavian vasile

In recent years, the softmax model and its fast approximations have become the de-facto loss functions for deep neural networks when dealing with multi-class prediction. This loss has been extended to language modeling and recommendation, two fields that fall into the framework of learning from Positive and Unlabeled data. In this paper, we stress the different drawbacks of the current family of softmax losses and sampling schemes when applied in a Positive and Unlabeled learning setup. We propose both a Relaxed Softmax loss (RS) and a new negative sampling scheme based on Boltzmann formulation. We show that the new training objective is better suited for the tasks of density estimation, item similarity and next-event prediction by driving uplifts in performance on textual and recommendation datasets against classical softmax.

📄 PDF Abstract BibTeX arXiv:1909.08079

Code (0)

등록된 구현이 없습니다.

Tasks

Density EstimationLanguage ModelingLanguage Modelling

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

Partially Mutual Exclusive Softmax for Positive and Unlabeled data

2019-05-01 · ICLR 2019 5 · Ugo Tanielian, Flavian vasile, Mike Gartrell

In recent years, softmax together with its fast approximations has become the de-facto loss function for deep neural networks with multiclass predictions. However, softmax is used in many problems that do not fully fit t…

Language ModelingLanguage Modelling

Gradient Estimation with Stochastic Softmax Tricks

2020-06-15 · NeurIPS 2020 12 · Max B. Paulus, Dami Choi, Daniel Tarlow, Andreas Krause 외

The Gumbel-Max trick is the basis of many relaxed gradient estimators. These estimators are easy to implement and low variance, but the goal of scaling them comprehensively to large combinatorial distributions is still o…

Nearest-Neighbor Inter-Intra Contrastive Learning from Unlabeled Videos

2023-03-13 · David Fan, Deyu Yang, Xinyu Li, Vimal Bhat 외

Contrastive learning has recently narrowed the gap between self-supervised and supervised methods in image and video domain. State-of-the-art video contrastive learning methods such as CVRL and $\rho$-MoCo spatiotemporal…

Contrastive LearningDiversity

Unsupervised Learning for Combinatorial Optimization with Principled Objective Relaxation

2022-07-13 · Haoyu Wang, Nan Wu, Hang Yang, Cong Hao 외

Using machine learning to solve combinatorial optimization (CO) problems is challenging, especially when the data is unlabeled. This work proposes an unsupervised learning framework for CO problems. Our framework follows…

Combinatorial Optimization

SLAY: Geometry-Aware Spherical Linearized Attention with Yat-Kernel

2026-02-04 · Jose Miguel Luna, Taha Bouhsine, Krzysztof Choromanski arxiv

We propose a new class of linear-time attention mechanisms based on a relaxed and computationally efficient formulation of the recently introduced E-Product, often referred to as the Yat-kernel (Bouhsine, 2025). The resu…