# Learning to Teach with Dynamic Loss Functions

arXiv: https://arxiv.org/abs/1810.12081 · HTML: https://mlsanity.com/paper/1810.12081/

## Key facts

- Cited by 40 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Oct 2018.

## Built on by (most cited first, 30 of 40)

- [Curriculum Learning: A Survey](https://mlsanity.com/paper/2101.10382/) (2021)
- [Human Pose Regression with Residual Log-likelihood Estimation](https://mlsanity.com/paper/2107.11291/) (2021)
- [Curriculum Temperature for Knowledge Distillation](https://mlsanity.com/paper/2211.16231/) (2022)
- [Knowledge Tracing: A Survey](https://mlsanity.com/paper/2201.06953/) (2022)
- [Meta-learning PINN loss functions](https://mlsanity.com/paper/2107.05544/) (2021)
- [Compute-Efficient Deep Learning: Algorithmic Trends and Opportunities](https://mlsanity.com/paper/2210.06640/) (2022)
- [Automated Progressive Learning for Efficient Training of Vision Transformers](https://mlsanity.com/paper/2203.14509/) (2022)
- [Tuning Language Models as Training Data Generators for Augmentation-Enhanced Few-Shot Learning](https://mlsanity.com/paper/2211.03044/) (2022)
- [Delving into Sample Loss Curve to Embrace Noisy and Imbalanced Data](https://mlsanity.com/paper/2201.00849/) (2021)
- [Searching for Robustness: Loss Learning for Noisy Classification Tasks](https://mlsanity.com/paper/2103.00243/) (2021)
- [Hundreds Guide Millions: Adaptive Offline Reinforcement Learning with Expert Guidance](https://mlsanity.com/paper/2309.01448/) (2023)
- [FORML: Learning to Reweight Data for Fairness](https://mlsanity.com/paper/2202.01719/) (2022)
- [Iterative Teaching by Label Synthesis](https://mlsanity.com/paper/2110.14432/) (2021)
- [MetricOpt: Learning to Optimize Black-Box Evaluation Metrics](https://mlsanity.com/paper/2104.10631/) (2021)
- [Learning Rate Curriculum](https://mlsanity.com/paper/2205.09180/) (2022)
- [Learning Symbolic Model-Agnostic Loss Functions via Meta-Learning](https://mlsanity.com/paper/2209.08907/) (2022)
- [Learning to Teach Fairness-aware Deep Multi-task Learning](https://mlsanity.com/paper/2206.08403/) (2022)
- [Iterative Teacher-Aware Learning](https://mlsanity.com/paper/2110.00137/) (2021)
- [Learning Data Teaching Strategies Via Knowledge Tracing](https://mlsanity.com/paper/2111.07083/) (2021)
- [Stochastic Re-weighted Gradient Descent via Distributionally Robust Optimization](https://mlsanity.com/paper/2306.09222/) (2023)
- [A Student-Teacher Architecture for Dialog Domain Adaptation under the Meta-Learning Setting](https://mlsanity.com/paper/2104.02689/) (2021)
- [Efficient Training of Large Vision Models via Advanced Automated Progressive Learning](https://mlsanity.com/paper/2410.00350/) (2024)
- [Vision-Based Anti Unmanned Aerial Technology: Opportunities and Challenges](https://mlsanity.com/paper/2507.10006/) (2025)
- [MSD: Saliency-aware Knowledge Distillation for Multimodal Understanding](https://mlsanity.com/paper/2101.01881/) (2021)
- [Improve Noise Tolerance of Robust Loss via Noise-Awareness](https://mlsanity.com/paper/2301.07306/) (2023)
- [The Power of Few: Accelerating and Enhancing Data Reweighting with Coreset Selection](https://mlsanity.com/paper/2403.12166/) (2024)
- [CBM: Curriculum by Masking](https://mlsanity.com/paper/2407.05193/) (2024)
- [L2T-DLN: Learning to Teach with Dynamic Loss Network](https://mlsanity.com/paper/2310.19313/) (2023)
- [MetaSeg: Content-Aware Meta-Net for Omni-Supervised Semantic Segmentation](https://mlsanity.com/paper/2401.11738/) (2024)
- [Reinforcement Teaching](https://mlsanity.com/paper/2204.11897/) (2022)

## Abstract (arXiv)

Teaching is critical to human society: it is with teaching that prospective students are educated and human civilization can be inherited and advanced. A good teacher not only provides his/her students with qualified teaching materials (e.g., textbooks), but also sets up appropriate learning objectives (e.g., course projects and exams) considering different situations of a student. When it comes to artificial intelligence, treating machine learning models as students, the loss functions that are optimized act as perfect counterparts of the learning objective set by the teacher. In this work, we explore the possibility of imitating human teaching behaviors by dynamically and automatically outputting appropriate loss functions to train machine learning models. Different from typical learning settings in which the loss function of a machine learning model is predefined and fixed, in our framework, the loss function of a machine learning model (we call it student) is defined by another machine learning model (we call it teacher). The ultimate goal of teacher model is cultivating the student to have better performance measured on development dataset. Towards that end, similar to human teaching, the teacher, a parametric model, dynamically outputs different loss functions that will be used and optimized by its student model at different training stages. We develop an efficient learning method for the teacher model that makes gradient based optimization possible, exempt of the ineffective solutions such as policy optimization. We name our method as "learning to teach with dynamic loss functions" (L2T-DLF for short). Extensive experiments on real world tasks including image classification and neural machine translation demonstrate that our method significantly improves the quality of various student models.