# Locality and compositionality in zero-shot learning

arXiv: https://arxiv.org/abs/1912.12179 · HTML: https://mlsanity.com/paper/1912.12179/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Dec 2019.

## Built on by (most cited first, 29 of 29)

- [Goal-Oriented Gaze Estimation for Zero-Shot Learning](https://mlsanity.com/paper/2103.03433/) (2021)
- [Independent Prototype Propagation for Zero-Shot Compositionality](https://mlsanity.com/paper/2106.00305/) (2021)
- [Open-vocabulary Attribute Detection](https://mlsanity.com/paper/2211.12914/) (2022)
- [How to Reuse and Compose Knowledge for a Lifetime of Tasks: A Survey on Continual Learning and Functional Composition](https://mlsanity.com/paper/2207.07730/) (2022)
- [Zero-shot Skeleton-based Action Recognition via Mutual Information Estimation and Maximization](https://mlsanity.com/paper/2308.03950/) (2023)
- [Cross-Trajectory Representation Learning for Zero-Shot Generalization in RL](https://mlsanity.com/paper/2106.02193/) (2021)
- [Attribute Prototype Network for Any-Shot Learning](https://mlsanity.com/paper/2204.01208/) (2022)
- [COMAE: COMprehensive Attribute Exploration for Zero-shot Hashing](https://mlsanity.com/paper/2402.16424/) (2024)
- [Zero-shot Node Classification with Decomposed Graph Prototype Network](https://mlsanity.com/paper/2106.08022/) (2021)
- [Cross-modal Representation Learning for Zero-shot Action Recognition](https://mlsanity.com/paper/2205.01657/) (2022)
- [Contrastive Attraction and Contrastive Repulsion for Representation Learning](https://mlsanity.com/paper/2105.03746/) (2021)
- [Region Semantically Aligned Network for Zero-Shot Learning](https://mlsanity.com/paper/2110.07130/) (2021)
- [Global Contrastive Batch Sampling via Optimization on Sample Permutations](https://mlsanity.com/paper/2210.12874/) (2022)
- [An Entropy-guided Reinforced Partial Convolutional Network for Zero-Shot Learning](https://mlsanity.com/paper/2111.02139/) (2021)
- [Diversity-boosted Generalization-Specialization Balancing for Zero-shot Learning](https://mlsanity.com/paper/2201.01961/) (2022)
- [Consciousness-Inspired Spatio-Temporal Abstractions for Better Generalization in Reinforcement Learning](https://mlsanity.com/paper/2310.00229/) (2023)
- [Learning Skill-Attributes for Transferable Assessment in Video](https://mlsanity.com/paper/2511.13993/) (2025)
- [LLM-TS Integrator: Integrating LLM for Enhanced Time Series Modeling](https://mlsanity.com/paper/2410.16489/) (2024)
- [Compositional Fine-Grained Low-Shot Learning](https://mlsanity.com/paper/2105.10438/) (2021)
- [Style-Content Disentanglement in Language-Image Pretraining Representations for Zero-Shot Sketch-to-Image Synthesis](https://mlsanity.com/paper/2206.01661/) (2022)
- [Self-supervised multimodal neuroimaging yields predictive representations for a spectrum of Alzheimer's phenotypes](https://mlsanity.com/paper/2209.02876/) (2022)
- [Concepts, Properties and an Approach for Compositional Generalization](https://mlsanity.com/paper/2102.04225/) (2021)
- [What Remains of Visual Semantic Embeddings](https://mlsanity.com/paper/2107.11991/) (2021)
- [The Sandbox Environment for Generalizable Agent Research (SEGAR)](https://mlsanity.com/paper/2203.10351/) (2022)
- [On a Built-in Conflict between Deep Learning and Systematic Generalization](https://mlsanity.com/paper/2208.11633/) (2022)
- [A Short Survey of Systematic Generalization](https://mlsanity.com/paper/2211.11956/) (2022)
- [Robust Reinforcement Learning Objectives for Sequential Recommender Systems](https://mlsanity.com/paper/2305.18820/) (2023)
- [ResNetVLLM -- Multi-modal Vision LLM for the Video Understanding Task](https://mlsanity.com/paper/2504.14432/) (2025)
- [Zero-Shot Skeleton-Based Action Anticipation](https://mlsanity.com/paper/2608.14243/) (2026)

## Abstract (arXiv)

In this work we study locality and compositionality in the context of learning representations for Zero Shot Learning (ZSL). In order to well-isolate the importance of these properties in learned representations, we impose the additional constraint that, differently from most recent work in ZSL, no pre-training on different datasets (e.g. ImageNet) is performed. The results of our experiments show how locality, in terms of small parts of the input, and compositionality, i.e. how well can the learned representations be expressed as a function of a smaller vocabulary, are both deeply related to generalization and motivate the focus on more local-aware models in future research directions for representation learning.