Evaluation of Latent Space Disentanglement in the Presence of Interdependent Attributes

10/11/2021
by   Karn N. Watcharasupat, et al.
0

Controllable music generation with deep generative models has become increasingly reliant on disentanglement learning techniques. However, current disentanglement metrics, such as mutual information gap (MIG), are often inadequate and misleading when used for evaluating latent representations in the presence of interdependent semantic attributes often encountered in real-world music datasets. In this work, we propose a dependency-aware information metric as a drop-in replacement for MIG that accounts for the inherent relationship between semantic attributes.

READ FULL TEXT

page 1

page 2

page 3

research
08/01/2021

Is Disentanglement enough? On Latent Representations for Controllable Music Generation

Improving controllability or the ability to manipulate one or more attri...
research
02/25/2020

Unsupervised Semantic Attribute Discovery and Control in Generative Models

This work focuses on the ability to control via latent space factors sem...
research
10/21/2021

Controllable and Compositional Generation with Latent-Space Energy-Based Models

Controllable generation is one of the key requirements for successful ad...
research
02/27/2023

Continuous descriptor-based control for deep audio synthesis

Despite significant advances in deep models for music generation, the us...
research
08/10/2023

Exploring XAI for the Arts: Explaining Latent Space in Generative Music

Explainable AI has the potential to support more interactive and fluid c...
research
08/17/2020

Learning Interpretable Representation for Controllable Polyphonic Music Generation

While deep generative models have become the leading methods for algorit...
research
12/20/2021

Latte: Cross-framework Python Package for Evaluation of Latent-Based Generative Models

Latte (for LATent Tensor Evaluation) is a Python library for evaluation ...

Please sign up or login with your details

Forgot password? Click here to reset