# Compositional Embeddings for Multi-Label One-Shot Learning

arXiv: https://arxiv.org/abs/2002.04193 · HTML: https://mlsanity.com/paper/2002.04193/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Feb 2020.

## Built on by (most cited first, 5 of 5)

- [Inferring Prototypes for Multi-Label Few-Shot Image Classification with Word Vector Guided Attention](https://mlsanity.com/paper/2112.01037/) (2021)
- [Compositional Clustering: Applications to Multi-Label Object Recognition and Speaker Identification](https://mlsanity.com/paper/2109.04160/) (2021)
- [Harnessing Geometric Constraints from Emotion Labels to improve Face Verification](https://mlsanity.com/paper/2103.03862/) (2021)
- [Modeling Multi-modal Cross-interaction for Multi-label Few-shot Image Classification Based on Local Feature Selection](https://mlsanity.com/paper/2412.13732/) (2024)
- [When Rule Violations Are Rare: Chimera Training for Logical Anomaly Detection](https://mlsanity.com/paper/2605.26171/) (2026)

## Abstract (arXiv)

We present a compositional embedding framework that infers not just a single class per input image, but a set of classes, in the setting of one-shot learning. Specifically, we propose and evaluate several novel models consisting of (1) an embedding function f trained jointly with a "composition" function g that computes set union operations between the classes encoded in two embedding vectors; and (2) embedding f trained jointly with a "query" function h that computes whether the classes encoded in one embedding subsume the classes encoded in another embedding. In contrast to prior work, these models must both perceive the classes associated with the input examples and encode the relationships between different class label sets, and they are trained using only weak one-shot supervision consisting of the label-set relationships among training examples. Experiments on the OmniGlot, Open Images, and COCO datasets show that the proposed compositional embedding models outperform existing embedding methods. Our compositional embedding models have applications to multi-label object recognition for both one-shot and supervised learning.