# Progressive Learning and Disentanglement of Hierarchical Representations

arXiv: https://arxiv.org/abs/2002.10549 · HTML: https://mlsanity.com/paper/2002.10549/

## Key facts

- Cited by 30 papers in the map (data through 7 Oct 2026).
- First posted on arXiv 24 Feb 2020.

## Built on by (most cited first, 30 of 30)

- [Disentangled Representation Learning](https://mlsanity.com/paper/2211.11695/) (2022)
- [Disentanglement via Latent Quantization](https://mlsanity.com/paper/2305.18378/) (2023)
- [Disentanglement of Correlated Factors via Hausdorff Factorized Support](https://mlsanity.com/paper/2210.07347/) (2022)
- [Diagonal Attention and Style-based GAN for Content-Style Disentanglement in Image Generation and Translation](https://mlsanity.com/paper/2103.16146/) (2021)
- [Task-Generic Hierarchical Human Motion Prior using VAEs](https://mlsanity.com/paper/2106.04004/) (2021)
- [Multi-Facet Clustering Variational Autoencoders](https://mlsanity.com/paper/2106.05241/) (2021)
- [Where and What? Examining Interpretable Disentangled Representations](https://mlsanity.com/paper/2104.05622/) (2021)
- [Commutative Lie Group VAE for Disentanglement Learning](https://mlsanity.com/paper/2106.03375/) (2021)
- [ProgFed: Effective, Communication, and Computation Efficient Federated Learning by Progressive Training](https://mlsanity.com/paper/2110.05323/) (2021)
- [Interaction Modeling with Multiplex Attention](https://mlsanity.com/paper/2208.10660/) (2022)
- [ProGAP: Progressive Graph Neural Networks with Differential Privacy Guarantees](https://mlsanity.com/paper/2304.08928/) (2023)
- [Disentanglement Analysis with Partial Information Decomposition](https://mlsanity.com/paper/2108.13753/) (2021)
- [Graph-based Unsupervised Disentangled Representation Learning via Multimodal Large Language Models](https://mlsanity.com/paper/2407.18999/) (2024)
- [Towards Robust Unsupervised Disentanglement of Sequential Data -- A Case Study Using Music Audio](https://mlsanity.com/paper/2205.05871/) (2022)
- [Learning Hierarchical Features with Joint Latent Space Energy-Based Prior](https://mlsanity.com/paper/2310.09604/) (2023)
- [Towards Unsupervised Content Disentanglement in Sentence Representations via Syntactic Roles](https://mlsanity.com/paper/2206.11184/) (2022)
- [Exploiting Inductive Bias in Transformers for Unsupervised Disentanglement of Syntax and Semantics with VAEs](https://mlsanity.com/paper/2205.05943/) (2022)
- [A Category-theoretical Meta-analysis of Definitions of Disentanglement](https://mlsanity.com/paper/2305.06886/) (2023)
- [Enriching Disentanglement: From Logical Definitions to Quantitative Metrics](https://mlsanity.com/paper/2305.11512/) (2023)
- [C2VAE: Gaussian Copula-based VAE Differing Disentangled from Coupled Representations with Contrastive Posterior](https://mlsanity.com/paper/2309.13303/) (2023)
- [Boxhead: A Dataset for Learning Hierarchical Representations](https://mlsanity.com/paper/2110.03628/) (2021)
- [Object Pursuit: Building a Space of Objects via Discriminative Weight Generation](https://mlsanity.com/paper/2112.07954/) (2021)
- [Pre-trained Multiple Latent Variable Generative Models are good defenders against Adversarial Attacks](https://mlsanity.com/paper/2412.03453/) (2024)
- [Enhancing Visual In-Context Learning by Multi-Faceted Fusion](https://mlsanity.com/paper/2601.10107/) (2026)
- [Interpretable Sentence Representation with Variational Autoencoders and Attention](https://mlsanity.com/paper/2305.02810/) (2023)
- [CAVACHON: a hierarchical variational autoencoder to integrate multi-modal single-cell data](https://mlsanity.com/paper/2405.18655/) (2024)
- [Towards an Improved Metric for Evaluating Disentangled Representations](https://mlsanity.com/paper/2410.03056/) (2024)
- [A Mutual Information Perspective on Multiple Latent Variable Generative Models for Positive View Generation](https://mlsanity.com/paper/2501.13718/) (2025)
- [Multiple Invertible and Partial-Equivariant Function for Latent Vector Transformation to Enhance Disentanglement in VAEs](https://mlsanity.com/paper/2502.03740/) (2025)
- [Causal Representation Learning on High-Dimensional Data: Benchmarks, Reproducibility, and Evaluation Metrics](https://mlsanity.com/paper/2603.17405/) (2026)

## Abstract (arXiv)

Learning rich representation from data is an important task for deep generative models such as variational auto-encoder (VAE). However, by extracting high-level abstractions in the bottom-up inference process, the goal of preserving all factors of variations for top-down generation is compromised. Motivated by the concept of "starting small", we present a strategy to progressively learn independent hierarchical representations from high- to low-levels of abstractions. The model starts with learning the most abstract representation, and then progressively grow the network architecture to introduce new representations at different levels of abstraction. We quantitatively demonstrate the ability of the presented model to improve disentanglement in comparison to existing works on two benchmark data sets using three disentanglement metrics, including a new metric we proposed to complement the previously-presented metric of mutual information gap. We further present both qualitative and quantitative evidence on how the progression of learning improves disentangling of hierarchical representations. By drawing on the respective advantage of hierarchical representation learning and progressive learning, this is to our knowledge the first attempt to improve disentanglement by progressively growing the capacity of VAE to learn hierarchical representations.