# Interpretable part-whole hierarchies and conceptual-semantic relationships in neural networks

arXiv: https://arxiv.org/abs/2203.03282 · HTML: https://mlsanity.com/paper/2203.03282/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 60 references that are in the map.
- First posted on arXiv 7 Mar 2022.

## Builds on (most cited first, 30 of 35)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [Implicit Neural Representations with Periodic Activation Functions](https://mlsanity.com/paper/2006.09661/) (2020)
- [MLP-Mixer: An all-MLP Architecture for Vision](https://mlsanity.com/paper/2105.01601/) (2021)
- [Show, Attend and Tell: Neural Image Caption Generation with Visual Attention](https://mlsanity.com/paper/1502.03044/) (2015)
- [Towards A Rigorous Science of Interpretable Machine Learning](https://mlsanity.com/paper/1702.08608/) (2017)
- [Explanation in Artificial Intelligence: Insights from the Social Sciences](https://mlsanity.com/paper/1706.07269/) (2017)
- [Transformers in Vision: A Survey](https://mlsanity.com/paper/2101.01169/) (2021)
- [Deep Networks with Stochastic Depth](https://mlsanity.com/paper/1603.09382/) (2016)
- [Revisiting Unreasonable Effectiveness of Data in Deep Learning Era](https://mlsanity.com/paper/1707.02968/) (2017)
- [Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations](https://mlsanity.com/paper/1906.01618/) (2019)
- [Dynamic Routing Between Capsules](https://mlsanity.com/paper/1710.09829/) (2017)
- [Cyclical Learning Rates for Training Neural Networks](https://mlsanity.com/paper/1506.01186/) (2015)
- [A Survey of Deep Learning Techniques for Autonomous Driving](https://mlsanity.com/paper/1910.07738/) (2019)
- [Interpretable machine learning: definitions, methods, and applications](https://mlsanity.com/paper/1901.04592/) (2019)
- [Financial Time Series Forecasting with Deep Learning : A Systematic Literature Review: 2005-2019](https://mlsanity.com/paper/1911.13288/) (2019)
- [How to represent part-whole hierarchies in a neural network](https://mlsanity.com/paper/2102.12627/) (2021)
- [Making Better Mistakes: Leveraging Class Hierarchies with Deep Networks](https://mlsanity.com/paper/1912.09393/) (2019)
- [Stacked Capsule Autoencoders](https://mlsanity.com/paper/1906.06818/) (2019)
- [Learning Physical Graph Representations from Visual Scenes](https://mlsanity.com/paper/2006.12373/) (2020)
- [Efficient-CapsNet: Capsule Network with Self-Attention Routing](https://mlsanity.com/paper/2101.12491/) (2021)
- [ConvMLP: Hierarchical Convolutional MLPs for Vision](https://mlsanity.com/paper/2109.04454/) (2021)

## Built on by (most cited first, 11 of 11)

- [Reversible Column Networks](https://mlsanity.com/paper/2212.11696/) (2022)
- [Representing Part-Whole Hierarchies in Foundation Models by Learning Localizability, Composability, and Decomposability from Anatomy via Self-Supervision](https://mlsanity.com/paper/2404.15672/) (2024)
- [On Occlusions in Video Action Detection: Benchmark Datasets And Training Recipes](https://mlsanity.com/paper/2410.19553/) (2024)
- [Asynchronous Perception Machine For Efficient Test-Time-Training](https://mlsanity.com/paper/2410.20535/) (2024)
- [Hybrid Gromov-Wasserstein Embedding for Capsule Learning](https://mlsanity.com/paper/2209.00232/) (2022)
- [Bridging Neural and Symbolic Representations with Transitional Dictionary Learning](https://mlsanity.com/paper/2308.02000/) (2023)
- [Enhance Sketch Recognition's Explainability via Semantic Component-Level Parsing](https://mlsanity.com/paper/2312.07875/) (2023)
- [FedPartWhole: Federated domain generalization via consistent part-whole hierarchies](https://mlsanity.com/paper/2407.14792/) (2024)
- [TCNL: Transparent and Controllable Network Learning Via Embedding Human-Guided Concepts](https://mlsanity.com/paper/2210.03274/) (2022)
- [Learning Latent Part-Whole Hierarchies for Point Clouds](https://mlsanity.com/paper/2211.07082/) (2022)
- [Canonical locks that encode part-whole hierarchies](https://mlsanity.com/paper/2609.26046/) (2026)

## Abstract (arXiv)

Deep neural networks achieve outstanding results in a large variety of tasks, often outperforming human experts. However, a known limitation of current neural architectures is the poor accessibility to understand and interpret the network response to a given input. This is directly related to the huge number of variables and the associated non-linearities of neural models, which are often used as black boxes. When it comes to critical applications as autonomous driving, security and safety, medicine and health, the lack of interpretability of the network behavior tends to induce skepticism and limited trustworthiness, despite the accurate performance of such systems in the given task. Furthermore, a single metric, such as the classification accuracy, provides a non-exhaustive evaluation of most real-world scenarios. In this paper, we want to make a step forward towards interpretability in neural networks, providing new tools to interpret their behavior. We present Agglomerator, a framework capable of providing a representation of part-whole hierarchies from visual cues and organizing the input distribution matching the conceptual-semantic hierarchical structure between classes. We evaluate our method on common datasets, such as SmallNORB, MNIST, FashionMNIST, CIFAR-10, and CIFAR-100, providing a more interpretable model than other state-of-the-art approaches.