# Beyond Losses Reweighting: Empowering Multi-Task Learning via the Generalization Perspective

arXiv: https://arxiv.org/abs/2211.13723 · HTML: https://mlsanity.com/paper/2211.13723/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 56 of its 86 references that are in the map.
- First posted on arXiv 24 Nov 2022.

## Builds on (most cited first, 30 of 56)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation](https://mlsanity.com/paper/1511.00561/) (2015)
- [Sharpness-Aware Minimization for Efficiently Improving Generalization](https://mlsanity.com/paper/2010.01412/) (2020)
- [Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics](https://mlsanity.com/paper/1705.07115/) (2017)
- [On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima](https://mlsanity.com/paper/1609.04836/) (2016)
- [Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift](https://mlsanity.com/paper/1906.02530/) (2019)
- [Gradient Surgery for Multi-Task Learning](https://mlsanity.com/paper/2001.06782/) (2020)
- [Averaging Weights Leads to Wider Optima and Better Generalization](https://mlsanity.com/paper/1803.05407/) (2018)
- [Visualizing the Loss Landscape of Neural Nets](https://mlsanity.com/paper/1712.09913/) (2017)
- [GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks](https://mlsanity.com/paper/1711.02257/) (2017)
- [Multi-Task Learning as Multi-Objective Optimization](https://mlsanity.com/paper/1810.04650/) (2018)
- [An Overview of Multi-Task Learning in Deep Neural Networks](https://mlsanity.com/paper/1706.05098/) (2017)
- [Exploring Generalization in Deep Learning](https://mlsanity.com/paper/1706.08947/) (2017)
- [Predictive Uncertainty Estimation via Prior Networks](https://mlsanity.com/paper/1802.10501/) (2018)
- [End-to-End Multi-Task Learning with Attention](https://mlsanity.com/paper/1803.10704/) (2018)
- [Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data](https://mlsanity.com/paper/1703.11008/) (2017)
- [Fantastic Generalization Measures and Where to Find Them](https://mlsanity.com/paper/1912.02178/) (2019)
- [Sharp Minima Can Generalize For Deep Nets](https://mlsanity.com/paper/1703.04933/) (2017)
- [Regularizing Neural Networks by Penalizing Confident Output Distributions](https://mlsanity.com/paper/1701.06548/) (2017)
- [Conflict-Averse Gradient Descent for Multi-task Learning](https://mlsanity.com/paper/2110.14048/) (2021)
- [SWAD: Domain Generalization by Seeking Flat Minima](https://mlsanity.com/paper/2102.08604/) (2021)
- [Entropy-SGD: Biasing Gradient Descent Into Wide Valleys](https://mlsanity.com/paper/1611.01838/) (2016)
- [Multi-Task Deep Neural Networks for Natural Language Understanding](https://mlsanity.com/paper/1901.11504/) (2019)
- [ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networks](https://mlsanity.com/paper/2102.11600/) (2021)
- [When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations](https://mlsanity.com/paper/2106.01548/) (2021)

## Built on by (most cited first, 15 of 15)

- [Selective Task Group Updates for Multi-Task Optimization](https://mlsanity.com/paper/2502.11986/) (2025)
- [Mitigating Parameter Interference in Model Merging via Sharpness-Aware Fine-Tuning](https://mlsanity.com/paper/2504.14662/) (2025)
- [Flat Seeking Bayesian Neural Networks](https://mlsanity.com/paper/2302.02713/) (2023)
- [Controllable Prompt Tuning For Balancing Group Distributional Robustness](https://mlsanity.com/paper/2403.02695/) (2024)
- [Enhancing Domain Adaptation through Prompt Gradient Alignment](https://mlsanity.com/paper/2406.09353/) (2024)
- [Beyond Reasoning Gains: Mitigating General-Capability Forgetting in Large Reasoning Models](https://mlsanity.com/paper/2510.21978/) (2025)
- [Unveiling m-Sharpness Through the Structure of Stochastic Gradient Noise](https://mlsanity.com/paper/2509.18001/) (2025)
- [Sharpness & Shift-Aware Self-Supervised Learning](https://mlsanity.com/paper/2305.10252/) (2023)
- [Diversity-Aware Agnostic Ensemble of Sharpness Minimizers](https://mlsanity.com/paper/2403.13204/) (2024)
- [Sharpness-Aware Minimization in Logit Space Efficiently Enhances Direct Preference Optimization](https://mlsanity.com/paper/2603.18258/) (2026)
- [DataFreeShield: Defending Adversarial Attacks without Training Data](https://mlsanity.com/paper/2406.15635/) (2024)
- [DGSAM: Domain Generalization via Individual Sharpness-Aware Minimization](https://mlsanity.com/paper/2503.23430/) (2025)
- [BoundarySeg:Boundary-Aware Multi-Task Learning for Semi-Supervised 3D Medical Image Segmentation with Limited Unlabeled Data](https://mlsanity.com/paper/2505.09829/) (2025)
- [Flatness and Gradient Alignment Are Both Necessary: Spectral-Aware Gradient-Aligned Exploration for Multi-Distribution Learning](https://mlsanity.com/paper/2605.07914/) (2026)
- [SUM: Unified Geometric Surgery on Spatio-Temporal Adaptation Vectors for Federated Class Incremental Learning](https://mlsanity.com/paper/2607.19384/) (2026)

## Abstract (arXiv)

Multi-task learning (MTL) trains deep neural networks to optimize several objectives simultaneously using a shared backbone, which leads to reduced computational costs, improved data efficiency, and enhanced performance through cross-task knowledge sharing. Although recent gradient manipulation techniques aim to find a common descent direction that benefits all tasks, conventional empirical loss minimization still leaves models vulnerable to overfitting and gradient conflicts. To address this, we introduce a novel MTL framework that leverages weight perturbation to regulate gradient norms, thus improving generalization. By adaptively modulating weight perturbations, our approach harmonizes task-specific gradients, reducing conflicts and encouraging more robust learning across tasks. Theoretical insights reveal that controlling the gradient norm through weight perturbation directly contributes to better generalization. Extensive experiments across diverse applications demonstrate that our method significantly outperforms existing gradient-based MTL techniques in terms of task performance and overall model robustness.