English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Disentanglement learning aims to construct independent and interpretablelatent variables in which generative models are a popular strategy. InfoGAN isa classic method via maximizing Mutual Information (MI) to obtain interpretablelatent variables mapped to the target space. However, it did not emphasizeindependent characteristic. To explicitly infer latent variables withinter-independence, we propose a novel GAN-based disentanglement framework viaembedding Orthogonal Basis Expansion (OBE) into InfoGAN network(Inference-InfoGAN) in an unsupervised way. Under the OBE module, one set oforthogonal basis can be adaptively found to expand arbitrary data withindependence property. To ensure the target-wise interpretable representation,we add a consistence constraint between the expansion coefficients and latentvariables on the base of MI maximization. Additionally, we design analternating optimization step on the consistence constraint and orthogonalrequirement updating, so that the training of Inference-InfoGAN can be moreconvenient. Finally, experiments validate that our proposed OBE module obtainsadaptive orthogonal basis, which can express better independent characteristicsthan fixed basis expression of Discrete Cosine Transform (DCT). To depict theperformance in downstream tasks, we compared with the state-of-the-artGAN-based and even VAE-based approaches on different datasets. OurInference-InfoGAN achieves higher disentanglement score in terms of FactorVAE,Separated Attribute Predictability (SAP), Mutual Information Gap (MIG) andVariation Predictability (VP) metrics without model fine-tuning. All theexperimental results illustrate that our method has inter-independenceinference ability because of the OBE module, and provides a good trade-offbetween it and target-wise interpretability of latent variables via jointingthe alternating optimization.

Inference-InfoGAN: Inference Independence via Embedding Orthogonal Basis Expansion