Associative Compression Networks

By Alex Graves, Jacob Menick, Aäron van den Oord. 2018

12 citations recorded by the source corpus.

Subfields: Representation & Self-Supervised Learning, Efficiency & Compression

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Representation & Self-Supervised Learning

1. Sander Dieleman
2. Karen Simonyan
3. Hugo Caselles-Dupré
4. David Filliat
5. Michaël Garcia Ortiz
6. Aäron van den Oord
7. James R. Glass
8. Abdel-rahman Mohamed

In Efficiency & Compression

1. Karen Simonyan
2. Sander Dieleman
3. David Filliat
4. Aäron van den Oord

Citations in the corpus

• Large Scale Adversarial Representation Learning (2019, neutral): “Associative compression networks (ACNs) [12] learn to compress at the dataset level by conditioning data on other previously transmitted data which are similar in code space, resulting in models that can “daydream” semantically similar samples, similar to BigBiGAN reconstructions.”
• The challenge of realistic music generation: modelling raw audio at scale (2018, methodology): “Other possibilities include using associative compression networks [17] or the ‘free bits’ method [26].”
• S-TRIGGER: Continual State Representation Learning via Self-Triggered Generative Replay (2019, background): “…model that is generative and reconstructs the input, which includes Varational Autoencoders (VAEs) and its many variants (e.g. β - VAE [8], ACN [6] and others) that are widely used for SRL. Previous work have shown that VAEs can learn continually using generated samples from previous tasks, a…”