# Task2Vec: Task Embedding for Meta-Learning

arXiv: https://arxiv.org/abs/1902.03545 · HTML: https://mlsanity.com/paper/1902.03545/

## Key facts

- Cited by 205 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Feb 2019.

## Built on by (most cited first, 30 of 205)

- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Editing Models with Task Arithmetic](https://mlsanity.com/paper/2212.04089/) (2022)
- [Merging Models with Fisher-Weighted Averaging](https://mlsanity.com/paper/2111.09832/) (2021)
- [SPoT: Better Frozen Model Adaptation through Soft Prompt Transfer](https://mlsanity.com/paper/2110.07904/) (2021)
- [Efficiently Identifying Task Groupings for Multi-Task Learning](https://mlsanity.com/paper/2109.04617/) (2021)
- [CrossFit: A Few-shot Learning Challenge for Cross-task Generalization in NLP](https://mlsanity.com/paper/2104.08835/) (2021)
- [Heterogeneous Risk Minimization](https://mlsanity.com/paper/2105.03818/) (2021)
- [Universal Model Routing for Efficient LLM Inference](https://mlsanity.com/paper/2502.08773/) (2025)
- [LoraRetriever: Input-Aware LoRA Retrieval and Composition for Mixed Tasks in the Wild](https://mlsanity.com/paper/2402.09997/) (2024)
- [What to Pre-Train on? Efficient Intermediate Task Selection](https://mlsanity.com/paper/2104.08247/) (2021)
- [OTCE: A Transferability Metric for Cross-Domain Cross-Task Representations](https://mlsanity.com/paper/2103.13843/) (2021)
- [Sharp-MAML: Sharpness-Aware Model-Agnostic Meta Learning](https://mlsanity.com/paper/2206.03996/) (2022)
- [Continual evaluation for lifelong learning: Identifying the stability gap](https://mlsanity.com/paper/2205.13452/) (2022)
- [A Survey on Model MoErging: Recycling and Routing Among Specialized Experts for Collaborative Learning](https://mlsanity.com/paper/2408.07057/) (2024)
- [MulT: An End-to-End Multitask Learning Transformer](https://mlsanity.com/paper/2205.08303/) (2022)
- [Frustratingly Easy Transferability Estimation](https://mlsanity.com/paper/2106.09362/) (2021)
- [Meta Flow Matching: Integrating Vector Fields on the Wasserstein Manifold](https://mlsanity.com/paper/2408.14608/) (2024)
- [A linearized framework and a new benchmark for model selection for fine-tuning](https://mlsanity.com/paper/2102.00084/) (2021)
- [Scalable Diverse Model Selection for Accessible Transfer Learning](https://mlsanity.com/paper/2111.06977/) (2021)
- [π-Tuning: Transferring Multimodal Foundation Models with Optimal Multi-task Interpolation](https://mlsanity.com/paper/2304.14381/) (2023)
- [Few-shot Image Generation via Adaptation-Aware Kernel Modulation](https://mlsanity.com/paper/2210.16559/) (2022)
- [Fast Adaptation with Linearized Neural Networks](https://mlsanity.com/paper/2103.01439/) (2021)
- [Model Spider: Learning to Rank Pre-Trained Models Efficiently](https://mlsanity.com/paper/2306.03900/) (2023)
- [Unleashing the Power of Data Tsunami: A Comprehensive Survey on Data Assessment and Selection for Instruction Tuning of Language Models](https://mlsanity.com/paper/2408.02085/) (2024)
- [Task2Sim : Towards Effective Pre-training and Transfer from Synthetic Data](https://mlsanity.com/paper/2112.00054/) (2021)
- [Wasserstein Task Embedding for Measuring Task Similarities](https://mlsanity.com/paper/2208.11726/) (2022)
- [Control Prefixes for Parameter-Efficient Text Generation](https://mlsanity.com/paper/2110.08329/) (2021)
- [Subspace Chronicles: How Linguistic Information Emerges, Shifts and Interacts during Language Model Training](https://mlsanity.com/paper/2310.16484/) (2023)
- [Exploring Incompatible Knowledge Transfer in Few-shot Image Generation](https://mlsanity.com/paper/2304.07574/) (2023)
- [Beyond Scale: The Diversity Coefficient as a Data Quality Metric for Variability in Natural Language Data](https://mlsanity.com/paper/2306.13840/) (2023)

## Abstract (arXiv)

We introduce a method to provide vectorial representations of visual classification tasks which can be used to reason about the nature of those tasks and their relations. Given a dataset with ground-truth labels and a loss function defined over those labels, we process images through a "probe network" and compute an embedding based on estimates of the Fisher information matrix associated with the probe network parameters. This provides a fixed-dimensional embedding of the task that is independent of details such as the number of classes and does not require any understanding of the class label semantics. We demonstrate that this embedding is capable of predicting task similarities that match our intuition about semantic and taxonomic relations between different visual tasks (e.g., tasks based on classifying different types of plants are similar) We also demonstrate the practical value of this framework for the meta-task of selecting a pre-trained feature extractor for a new task. We present a simple meta-learning framework for learning a metric on embeddings that is capable of predicting which feature extractors will perform well. Selecting a feature extractor with task embedding obtains a performance close to the best available feature extractor, while costing substantially less than exhaustively training and evaluating on all available feature extractors.