# On Leveraging Variational Graph Embeddings for Open World Compositional Zero-Shot Learning

arXiv: https://arxiv.org/abs/2204.11848 · HTML: https://mlsanity.com/paper/2204.11848/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 50 references that are in the map.
- First posted on arXiv 23 Apr 2022.

## Builds on (most cited first, 27 of 27)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Enriching Word Vectors with Subword Information](https://mlsanity.com/paper/1607.04606/) (2016)
- [Variational Graph Auto-Encoders](https://mlsanity.com/paper/1611.07308/) (2016)
- [AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty](https://mlsanity.com/paper/1912.02781/) (2019)
- [Simple and Deep Graph Convolutional Networks](https://mlsanity.com/paper/2007.02133/) (2020)
- [A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges](https://mlsanity.com/paper/2011.06225/) (2020)
- [Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Ugly](https://mlsanity.com/paper/1707.00600/) (2017)
- [Tutorial on Variational Autoencoders](https://mlsanity.com/paper/1606.05908/) (2016)
- [A Metric Learning Reality Check](https://mlsanity.com/paper/2003.08505/) (2020)
- [Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradients](https://mlsanity.com/paper/1711.09404/) (2017)
- [Composing Text and Image for Image Retrieval - An Empirical Odyssey](https://mlsanity.com/paper/1812.07119/) (2018)
- [An Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the Wild](https://mlsanity.com/paper/1605.04253/) (2016)
- [Task-Driven Modular Networks for Zero-Shot Compositional Learning](https://mlsanity.com/paper/1905.05908/) (2019)
- [Learning Graph Embeddings for Compositional Zero-shot Learning](https://mlsanity.com/paper/2102.01987/) (2021)
- [Open World Compositional Zero-Shot Learning](https://mlsanity.com/paper/2101.12609/) (2021)
- [Symmetry and Group in Attribute-Object Compositions](https://mlsanity.com/paper/2004.00587/) (2020)
- [Compositional Learning of Image-Text Query for Image Retrieval](https://mlsanity.com/paper/2006.11149/) (2020)
- [Semantic Jitter: Dense Supervision for Visual Comparisons via Synthetic Images](https://mlsanity.com/paper/1612.06341/) (2016)
- [Zero Shot Recognition with Unreliable Attributes](https://mlsanity.com/paper/1409.4327/) (2014)
- [Recovering the Missing Link: Predicting Class-Attribute Associations for Unsupervised Zero-Shot Learning](https://mlsanity.com/paper/1610.04787/) (2016)
- [Morphosyntactic Tagging with a Meta-BiLSTM Model over Context Sensitive Token Encodings](https://mlsanity.com/paper/1805.08237/) (2018)

## Built on by (most cited first, 13 of 13)

- [Learning Conditional Attributes for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2305.17940/) (2023)
- [Troika: Multi-Path Cross-Modal Traction for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2303.15230/) (2023)
- [Context-based and Diversity-driven Specificity in Compositional Zero-Shot Learning](https://mlsanity.com/paper/2402.17251/) (2024)
- [Learning Clustering-based Prototypes for Compositional Zero-shot Learning](https://mlsanity.com/paper/2502.06501/) (2025)
- [Compositional Zero-shot Learning via Progressive Language-based Observations](https://mlsanity.com/paper/2311.14749/) (2023)
- [On the Element-Wise Representation and Reasoning in Zero-Shot Image Recognition: A Systematic Survey](https://mlsanity.com/paper/2408.04879/) (2024)
- [Learning Visual Proxy for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2501.13859/) (2025)
- [A Conditional Probability Framework for Compositional Zero-shot Learning](https://mlsanity.com/paper/2507.17377/) (2025)
- [MAC: A Benchmark for Multiple Attributes Compositional Zero-Shot Learning](https://mlsanity.com/paper/2406.12757/) (2024)
- [CAMS: Towards Compositional Zero-Shot Learning via Gated Cross-Attention and Multi-Space Disentanglement](https://mlsanity.com/paper/2511.16378/) (2025)
- [H2em: Learning Hierarchical Hyperbolic Embeddings for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2512.20029/) (2025)
- [Semantically Guided Dynamic Visual Prototype Refinement for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2501.07114/) (2025)
- [Structure-aware Prompt Adaptation from Seen to Unseen for Open-Vocabulary Compositional Zero-Shot Learning](https://mlsanity.com/paper/2603.03815/) (2026)

## Abstract (arXiv)

Humans are able to identify and categorize novel compositions of known concepts. The task in Compositional Zero-Shot learning (CZSL) is to learn composition of primitive concepts, i.e. objects and states, in such a way that even their novel compositions can be zero-shot classified. In this work, we do not assume any prior knowledge on the feasibility of novel compositions i.e.open-world setting, where infeasible compositions dominate the search space. We propose a Compositional Variational Graph Autoencoder (CVGAE) approach for learning the variational embeddings of the primitive concepts (nodes) as well as feasibility of their compositions (via edges). Such modelling makes CVGAE scalable to real-world application scenarios. This is in contrast to SOTA method, CGE, which is computationally very expensive. e.g.for benchmark C-GQA dataset, CGE requires 3.94 x 10^5 nodes, whereas CVGAE requires only 1323 nodes. We learn a mapping of the graph and image embeddings onto a common embedding space. CVGAE adopts a deep metric learning approach and learns a similarity metric in this space via bi-directional contrastive loss between projected graph and image embeddings. We validate the effectiveness of our approach on three benchmark datasets.We also demonstrate via an image retrieval task that the representations learnt by CVGAE are better suited for compositional generalization.