# TVAE: Triplet-Based Variational Autoencoder using Metric Learning

arXiv: https://arxiv.org/abs/1802.04403 · HTML: https://mlsanity.com/paper/1802.04403/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Feb 2018.

## Built on by (most cited first, 18 of 18)

- [High-Dimensional Bayesian Optimisation with Variational Autoencoders and Deep Metric Learning](https://mlsanity.com/paper/2106.03609/) (2021)
- [StyleMeUp: Towards Style-Agnostic Sketch-Based Image Retrieval](https://mlsanity.com/paper/2103.15706/) (2021)
- [OCT-GAN: Neural ODE-based Conditional Tabular GANs](https://mlsanity.com/paper/2105.14969/) (2021)
- [Invertible Tabular GANs: Killing Two Birds with OneStone for Tabular Data Synthesis](https://mlsanity.com/paper/2202.03636/) (2022)
- [An Empirical Study on the Membership Inference Attack against Tabular Data Synthesis Models](https://mlsanity.com/paper/2208.08114/) (2022)
- [Cross-Modal Fusion Distillation for Fine-Grained Sketch-Based Image Retrieval](https://mlsanity.com/paper/2210.10486/) (2022)
- [Cooperative Decentralized Backdoor Attacks on Vertical Federated Learning](https://mlsanity.com/paper/2501.09320/) (2025)
- [Synthetic Data Generation for Augmenting Small Samples](https://mlsanity.com/paper/2501.18741/) (2025)
- [Freeview Sketching: View-Aware Fine-Grained Sketch-Based Image Retrieval](https://mlsanity.com/paper/2407.01810/) (2024)
- [Dimensionality Reduction Techniques for Global Bayesian Optimisation](https://mlsanity.com/paper/2412.09183/) (2024)
- [Intervening to Learn and Compose Causally Disentangled Representations](https://mlsanity.com/paper/2507.04754/) (2025)
- [TabKD: Tabular Knowledge Distillation through Interaction Diversity of Learned Feature Bins](https://mlsanity.com/paper/2603.15481/) (2026)
- [Self-Reinforcing Controllable Synthesis of Rare Relational Data via Bayesian Calibration](https://mlsanity.com/paper/2604.16817/) (2026)
- [A Distance Metric Learning Model Based On Variational Information Bottleneck](https://mlsanity.com/paper/2403.02794/) (2024)
- [Nonlinear Dimensionality Reduction Techniques for Bayesian Optimization](https://mlsanity.com/paper/2510.15435/) (2025)
- [CTTVAE: Latent Space Structuring for Conditional Tabular Data Generation on Imbalanced Datasets](https://mlsanity.com/paper/2602.03641/) (2026)
- [Machine learning models for estimating counterfactuals in a single-arm inflammatory bowel disease study](https://mlsanity.com/paper/2604.23465/) (2026)
- [Constrained Tabular Diffusion for Finance](https://mlsanity.com/paper/2606.28674/) (2026)

## Abstract (arXiv)

Deep metric learning has been demonstrated to be highly effective in learning semantic representation and encoding information that can be used to measure data similarity, by relying on the embedding learned from metric learning. At the same time, variational autoencoder (VAE) has widely been used to approximate inference and proved to have a good performance for directed probabilistic models. However, for traditional VAE, the data label or feature information are intractable. Similarly, traditional representation learning approaches fail to represent many salient aspects of the data. In this project, we propose a novel integrated framework to learn latent embedding in VAE by incorporating deep metric learning. The features are learned by optimizing a triplet loss on the mean vectors of VAE in conjunction with standard evidence lower bound (ELBO) of VAE. This approach, which we call Triplet based Variational Autoencoder (TVAE), allows us to capture more fine-grained information in the latent embedding. Our model is tested on MNIST data set and achieves a high triplet accuracy of 95.60% while the traditional VAE (Kingma & Welling, 2013) achieves triplet accuracy of 75.08%.