# Unsupervised Meta-Learning through Latent-Space Interpolation in Generative Models

arXiv: https://arxiv.org/abs/2006.10236 · HTML: https://mlsanity.com/paper/2006.10236/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Jun 2020.

## Built on by (most cited first, 26 of 26)

- [Advances and Challenges in Meta-Learning: A Technical Review](https://mlsanity.com/paper/2307.04722/) (2023)
- [AID: Attention Interpolation of Text-to-Image Diffusion](https://mlsanity.com/paper/2403.17924/) (2024)
- [Self-Supervision Can Be a Good Few-Shot Learner](https://mlsanity.com/paper/2207.09176/) (2022)
- [Unsupervised Meta-Learning via Few-shot Pseudo-supervised Contrastive Learning](https://mlsanity.com/paper/2303.00996/) (2023)
- [On the Importance of Distractors for Few-Shot Classification](https://mlsanity.com/paper/2109.09883/) (2021)
- [A Survey of the Self Supervised Learning Mechanisms for Vision Transformers](https://mlsanity.com/paper/2408.17059/) (2024)
- [ProtoTransformer: A Meta-Learning Approach to Providing Student Feedback](https://mlsanity.com/paper/2107.14035/) (2021)
- [Dream to Adapt: Meta Reinforcement Learning by Latent Context Imagination and MDP Imagination](https://mlsanity.com/paper/2311.06673/) (2023)
- [BECLR: Batch Enhanced Contrastive Few-Shot Learning](https://mlsanity.com/paper/2402.02444/) (2024)
- [Is Meta-Learning Out? Rethinking Unsupervised Few-Shot Classification with Limited Entropy](https://mlsanity.com/paper/2509.13185/) (2025)
- [Rethinking Clustering-Based Pseudo-Labeling for Unsupervised Meta-Learning](https://mlsanity.com/paper/2209.13635/) (2022)
- [CMVAE: Causal Meta VAE for Unsupervised Meta-Learning](https://mlsanity.com/paper/2302.09731/) (2023)
- [Unsupervised Meta-Learning via In-Context Learning](https://mlsanity.com/paper/2405.16124/) (2024)
- [Self-Supervised Class-Cognizant Few-Shot Classification](https://mlsanity.com/paper/2202.08149/) (2022)
- [Unsupervised Few-shot Learning via Deep Laplacian Eigenmaps](https://mlsanity.com/paper/2210.03595/) (2022)
- [Unleash Model Potential: Bootstrapped Meta Self-supervised Learning](https://mlsanity.com/paper/2308.14267/) (2023)
- [DRESS: Disentangled Representation-based Self-Supervised Meta-Learning for Diverse Tasks](https://mlsanity.com/paper/2503.09679/) (2025)
- [Unsupervised Episode Generation for Graph Meta-learning](https://mlsanity.com/paper/2306.15217/) (2023)
- [RAFIC: Retrieval-Augmented Few-shot Image Classification](https://mlsanity.com/paper/2312.06868/) (2023)
- [SelfReplay: Adapting Self-Supervised Sensory Models via Adaptive Meta-Task Replay](https://mlsanity.com/paper/2404.15305/) (2024)
- [On the Universality of Self-Supervised Learning](https://mlsanity.com/paper/2405.01053/) (2024)
- [Neural Routing in Meta Learning](https://mlsanity.com/paper/2210.07932/) (2022)
- [Unsupervised Meta-Learning via Dynamic Head and Heterogeneous Task Construction for Few-Shot Classification](https://mlsanity.com/paper/2410.02267/) (2024)
- [Uncertainty-DTW for Sequences and Visual Tokens](https://mlsanity.com/paper/2605.25110/) (2026)
- [An Information Theoretic Framework for Graph Novelty Generation via Latent Mixture Modeling](https://mlsanity.com/paper/2606.19770/) (2026)
- [Improving Generalization and Robustness in Offline Reinforcement Learning via Boundary-Aware Data Augmentation](https://mlsanity.com/paper/2609.20300/) (2026)

## Abstract (arXiv)

Unsupervised meta-learning approaches rely on synthetic meta-tasks that are created using techniques such as random selection, clustering and/or augmentation. Unfortunately, clustering and augmentation are domain-dependent, and thus they require either manual tweaking or expensive learning. In this work, we describe an approach that generates meta-tasks using generative models. A critical component is a novel approach of sampling from the latent space that generates objects grouped into synthetic classes forming the training and validation data of a meta-task. We find that the proposed approach, LAtent Space Interpolation Unsupervised Meta-learning (LASIUM), outperforms or is competitive with current unsupervised learning baselines on few-shot classification tasks on the most widely used benchmark datasets. In addition, the approach promises to be applicable without manual tweaking over a wider range of domains than previous approaches.