# Curriculum Learning of Multiple Tasks

arXiv: https://arxiv.org/abs/1412.1353 · HTML: https://mlsanity.com/paper/1412.1353/

## Key facts

- Cited by 66 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Dec 2014.

## Built on by (most cited first, 30 of 66)

- [FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling](https://mlsanity.com/paper/2110.08263/) (2021)
- [Curriculum Learning: A Survey](https://mlsanity.com/paper/2101.10382/) (2021)
- [Boosting the Generalization and Reasoning of Vision Language Models with Curriculum Reinforcement Learning](https://mlsanity.com/paper/2503.07065/) (2025)
- [Uncertainty-Aware Unsupervised Domain Adaptation in Object Detection](https://mlsanity.com/paper/2103.00236/) (2021)
- [MMedAgent-RL: Optimizing Multi-Agent Collaboration for Multimodal Medical Reasoning](https://mlsanity.com/paper/2506.00555/) (2025)
- [Continual Learning in Linear Classification on Separable Data](https://mlsanity.com/paper/2306.03534/) (2023)
- [The Effect of Task Ordering in Continual Learning](https://mlsanity.com/paper/2205.13323/) (2022)
- [An Analytical Theory of Curriculum Learning in Teacher-Student Networks](https://mlsanity.com/paper/2106.08068/) (2021)
- [ASP: Learn a Universal Neural Solver!](https://mlsanity.com/paper/2303.00466/) (2023)
- [Denoising Task Difficulty-based Curriculum for Training Diffusion Models](https://mlsanity.com/paper/2403.10348/) (2024)
- [Medical Image Segmentation with Limited Supervision: A Review of Deep Network Models](https://mlsanity.com/paper/2103.00429/) (2021)
- [Provable Advantage of Curriculum Learning on Parity Targets with Mixed Inputs](https://mlsanity.com/paper/2306.16921/) (2023)
- [CL-MAE: Curriculum-Learned Masked Autoencoders](https://mlsanity.com/paper/2308.16572/) (2023)
- [CurricuLLM: Automatic Task Curricula Design for Learning Complex Robot Skills using Large Language Models](https://mlsanity.com/paper/2409.18382/) (2024)
- [Gradual Domain Adaptation in the Wild:When Intermediate Distributions are Absent](https://mlsanity.com/paper/2106.06080/) (2021)
- [Domain Generalization via Balancing Training Difficulty and Model Capability](https://mlsanity.com/paper/2309.00844/) (2023)
- [Optimal Task Order for Continual Learning of Multiple Tasks](https://mlsanity.com/paper/2502.03350/) (2025)
- [RecGPT Technical Report](https://mlsanity.com/paper/2507.22879/) (2025)
- [Coarse-to-Fine Curriculum Learning](https://mlsanity.com/paper/2106.04072/) (2021)
- [Traffic-Domain Video Question Answering with Automatic Captioning](https://mlsanity.com/paper/2307.09636/) (2023)
- [Learning Rate Curriculum](https://mlsanity.com/paper/2205.09180/) (2022)
- [When Do Curricula Work in Federated Learning?](https://mlsanity.com/paper/2212.12712/) (2022)
- [From Zero to Hero: Advancing Zero-Shot Foundation Models for Tabular Outlier Detection](https://mlsanity.com/paper/2602.03018/) (2026)
- [Let the Model Decide its Curriculum for Multitask Learning](https://mlsanity.com/paper/2205.09898/) (2022)
- [MM-Align: Learning Optimal Transport-based Alignment Dynamics for Fast and Accurate Inference on Missing Modality Sequences](https://mlsanity.com/paper/2210.12798/) (2022)
- [Curriculum-based Asymmetric Multi-task Reinforcement Learning](https://mlsanity.com/paper/2211.03352/) (2022)
- [RecRecNet: Rectangling Rectified Wide-Angle Images by Thin-Plate Spline Model and DoF-based Curriculum Learning](https://mlsanity.com/paper/2301.01661/) (2023)
- [How to distribute data across tasks for meta-learning?](https://mlsanity.com/paper/2103.08463/) (2021)
- [Out of Thin Air: Exploring Data-Free Adversarial Robustness Distillation](https://mlsanity.com/paper/2303.11611/) (2023)
- [Stochastic Re-weighted Gradient Descent via Distributionally Robust Optimization](https://mlsanity.com/paper/2306.09222/) (2023)

## Abstract (arXiv)

Sharing information between multiple tasks enables algorithms to achieve good generalization performance even from small amounts of training data. However, in a realistic scenario of multi-task learning not all tasks are equally related to each other, hence it could be advantageous to transfer information only between the most related tasks. In this work we propose an approach that processes multiple tasks in a sequence with sharing between subsequent tasks instead of solving all tasks jointly. Subsequently, we address the question of curriculum learning of tasks, i.e. finding the best order of tasks to be learned. Our approach is based on a generalization bound criterion for choosing the task order that optimizes the average expected classification performance over all tasks. Our experimental results show that learning multiple related tasks sequentially can be more effective than learning them jointly, the order in which tasks are being solved affects the overall performance, and that our model is able to automatically discover the favourable order of tasks.