# The Impact of Negative Sampling on Contrastive Structured World Models

arXiv: https://arxiv.org/abs/2107.11676 · HTML: https://mlsanity.com/paper/2107.11676/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Latent dynamics models and model-based RL, one of 11 directions in World models.
- Builds on 25 of its 33 references that are in the map.
- First posted on arXiv 24 Jul 2021.

## Placed in

- World models / [Latent dynamics models and model-based RL](https://mlsanity.com/wm/latent-dynamics-models-and-model-based-rl/)

## Builds on (most cited first, 25 of 25)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Asynchronous Methods for Deep Reinforcement Learning](https://mlsanity.com/paper/1602.01783/) (2016)
- [node2vec: Scalable Feature Learning for Networks](https://mlsanity.com/paper/1607.00653/) (2016)
- [Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination](https://mlsanity.com/paper/1805.01978/) (2018)
- [Variational Graph Auto-Encoders](https://mlsanity.com/paper/1611.07308/) (2016)
- [Learning deep representations by mutual information estimation and maximization](https://mlsanity.com/paper/1808.06670/) (2018)
- [CURL: Contrastive Unsupervised Representations for Reinforcement Learning](https://mlsanity.com/paper/2004.04136/) (2020)
- [Time-Contrastive Networks: Self-Supervised Learning from Video](https://mlsanity.com/paper/1704.06888/) (2017)
- [MONet: Unsupervised Scene Decomposition and Representation](https://mlsanity.com/paper/1901.11390/) (2019)
- [Multi-Object Representation Learning with Iterative Variational Inference](https://mlsanity.com/paper/1903.00450/) (2019)
- [Discriminative Unsupervised Feature Learning with Exemplar Convolutional Neural Networks](https://mlsanity.com/paper/1406.6909/) (2014)
- [On the Binding Problem in Artificial Neural Networks](https://mlsanity.com/paper/2012.05208/) (2020)
- [GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations](https://mlsanity.com/paper/1907.13052/) (2019)
- [Contrastive Learning of Structured World Models](https://mlsanity.com/paper/1911.12247/) (2019)
- [Learning Robust Representations via Multi-View Information Bottleneck](https://mlsanity.com/paper/2002.07017/) (2020)
- [Entity Abstraction in Visual Model-Based Reinforcement Learning](https://mlsanity.com/paper/1910.12827/) (2019)
- [Visual Interaction Networks](https://mlsanity.com/paper/1706.01433/) (2017)
- [Plannable Approximations to MDP Homomorphisms: Equivariance under Actions](https://mlsanity.com/paper/2002.11963/) (2020)
- [Reasoning About Physical Interactions with Object-Oriented Prediction and Planning](https://mlsanity.com/paper/1812.10972/) (2018)
- [Structured Object-Aware Physics Prediction for Video Modeling and Planning](https://mlsanity.com/paper/1910.02425/) (2019)
- [Learning Object-Centric Video Models by Contrasting Sets](https://mlsanity.com/paper/2011.10287/) (2020)
- [A Perspective on Objects and Systematic Generalization in Model-Based RL](https://mlsanity.com/paper/1906.01035/) (2019)
- [Slot Contrastive Networks: A Contrastive Approach for Representing Objects](https://mlsanity.com/paper/2007.09294/) (2020)

## Built on by (most cited first, 2 of 2)

- [Toward Compositional Generalization in Object-Oriented World Modeling](https://mlsanity.com/paper/2204.13661/) (2022)
- [Binding Actions to Objects in World Models](https://mlsanity.com/paper/2204.13022/) (2022)

## Abstract (arXiv)

World models trained by contrastive learning are a compelling alternative to autoencoder-based world models, which learn by reconstructing pixel states. In this paper, we describe three cases where small changes in how we sample negative states in the contrastive loss lead to drastic changes in model performance. In previously studied Atari datasets, we show that leveraging time step correlations can double the performance of the Contrastive Structured World Model. We also collect a full version of the datasets to study contrastive learning under a more diverse set of experiences.