# Importance of negative sampling in weak label learning

arXiv: https://arxiv.org/abs/2309.13227 · HTML: https://mlsanity.com/paper/2309.13227/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 23 references that are in the map.
- First posted on arXiv 23 Sep 2023.

## Builds on (most cited first, 13 of 13)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds](https://mlsanity.com/paper/1906.03671/) (2019)
- [Understanding Negative Sampling in Graph Representation Learning](https://mlsanity.com/paper/2005.09863/) (2020)
- [Learning from Between-class Examples for Deep Sound Recognition](https://mlsanity.com/paper/1711.10282/) (2017)
- [NSCaching: Simple and Efficient Negative Sampling for Knowledge Graph Embedding](https://mlsanity.com/paper/1812.06410/) (2018)
- [Structure Aware Negative Sampling in Knowledge Graphs](https://mlsanity.com/paper/2009.11355/) (2020)
- [Audio Event Detection using Weakly Labeled Data](https://mlsanity.com/paper/1605.02401/) (2016)
- [A Closer Look at Weak Label Learning for Audio Events](https://mlsanity.com/paper/1804.09288/) (2018)
- [Learning to Sample: an Active Learning Framework](https://mlsanity.com/paper/1909.03585/) (2019)
- [Disentangling Sampling and Labeling Bias for Learning in Large-Output Spaces](https://mlsanity.com/paper/2105.05736/) (2021)
- [Active Learning from Positive and Unlabeled Data](https://mlsanity.com/paper/1602.07495/) (2016)
- [Training image classifiers using Semi-Weak Label Data](https://mlsanity.com/paper/2103.10608/) (2021)

## Built on by (most cited first, 1 of 1)

- [Deciphering GunType Hierarchy through Acoustic Analysis of Gunshot Recordings](https://mlsanity.com/paper/2506.20609/) (2025)

## Abstract (arXiv)

Weak-label learning is a challenging task that requires learning from data "bags" containing positive and negative instances, but only the bag labels are known. The pool of negative instances is usually larger than positive instances, thus making selecting the most informative negative instance critical for performance. Such a selection strategy for negative instances from each bag is an open problem that has not been well studied for weak-label learning. In this paper, we study several sampling strategies that can measure the usefulness of negative instances for weak-label learning and select them accordingly. We test our method on CIFAR-10 and AudioSet datasets and show that it improves the weak-label classification performance and reduces the computational cost compared to random sampling methods. Our work reveals that negative instances are not all equally irrelevant, and selecting them wisely can benefit weak-label learning.