Cover Image

Task Weighting through Gradient Projection for Multitask Learning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Bohn, Christian, Freeman, Ido, Tercan, Hasan, Meisen, Tobias
Format:	Preprint
Published:	2024
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Efficient Inter-Task Attention for Multitask Transformer Models
by: Bohn, Christian, et al.
Published: (2025)

Graph Query Networks for Object Detection with Automotive Radar
by: Saini, Loveneet, et al.
Published: (2025)

schlably: A Python Framework for Deep Reinforcement Learning Based Scheduling Experiments
by: de Puiseau, Constantin Waubert, et al.
Published: (2023)

Beyond Training: Optimizing Reinforcement Learning Based Job Shop Scheduling Through Adaptive Action Sampling
by: de Puiseau, Constantin Waubert, et al.
Published: (2024)

EXCODER: EXplainable Classification Of DiscretE time series Representations
by: Hahn, Yannik, et al.
Published: (2026)

Out of Distribution Detection for Efficient Continual Learning in Quality Prediction for Arc Welding
by: Hahn, Yannik, et al.
Published: (2025)

Decision Transformer for Enhancing Neural Local Search on the Job Shop Scheduling Problem
by: de Puiseau, Constantin Waubert, et al.
Published: (2024)

Towards Lifelong Learning Embeddings: An Algorithmic Approach to Dynamically Extend Embeddings
by: Gomes, Miguel Alves, et al.
Published: (2024)

Rethinking Backbone Design for Lightweight 3D Object Detection in LiDAR
by: Chandorkar, Adwait, et al.
Published: (2025)

Detection Transformers Under the Knife: A Neuroscience-Inspired Approach to Ablations
by: Hütten, Nils, et al.
Published: (2025)

AttentiveGRU: Recurrent Spatio-Temporal Modeling for Advanced Radar-Based BEV Object Detection
by: Saini, Loveneet, et al.
Published: (2025)

Thresholded Lexicographic Ordered Multiobjective Reinforcement Learning
by: Tercan, Alperen, et al.
Published: (2024)

Scalable Multitask Learning Using Gradient-based Estimation of Task Affinity
by: Li, Dongyue, et al.
Published: (2024)

Failure Modes for Deep Learning-Based Online Mapping: How to Measure and Address Them
by: Hubbertz, Michael, et al.
Published: (2026)

Boosting Multitask Learning on Graphs through Higher-Order Task Affinities
by: Li, Dongyue, et al.
Published: (2023)

$α$VIL: Learning to Leverage Auxiliary Tasks for Multitask Learning
by: Kourdis, Rafael, et al.
Published: (2024)

Initial Distribution Sensitivity of Constrained Markov Decision Processes
by: Tercan, Alperen, et al.
Published: (2025)

Multitask Learning with Learned Task Relationships
by: Wan, Zirui, et al.
Published: (2025)

Efficient Reward Identification In Max Entropy Reinforcement Learning with Sparsity and Rank Priors
by: Shehab, Mohamad Louai, et al.
Published: (2025)

Improved Single Camera BEV Perception Using Multi-Camera Training
by: Busch, Daniel, et al.
Published: (2024)

Rectify, Don't Regret: Avoiding Pitfalls of Differentiable Simulation in Trajectory Prediction
by: Yadav, Harsh, et al.
Published: (2026)

Task-Agnostic Federated Continual Learning via Replay-Free Gradient Projection
by: Cha, Seohyeon, et al.
Published: (2025)

Principled Federated Domain Adaptation: Gradient Projection and Auto-Weighting
by: Jiang, Enyi, et al.
Published: (2023)

Sample Efficient Myopic Exploration Through Multitask Reinforcement Learning with Diverse Tasks
by: Xu, Ziping, et al.
Published: (2024)

Learning Representation for Multitask learning through Self Supervised Auxiliary learning
by: Shin, Seokwon, et al.
Published: (2024)

AWP: Activation-Aware Weight Pruning and Quantization with Projected Gradient Descent
by: Liu, Jing, et al.
Published: (2025)

CASPFormer: Trajectory Prediction from BEV Images with Deformable Attention
by: Yadav, Harsh, et al.
Published: (2024)

LMFormer: Lane based Motion Prediction Transformer
by: Yadav, Harsh, et al.
Published: (2025)

Cross-Task Affinity Learning for Multitask Dense Scene Predictions
by: Sinodinos, Dimitrios, et al.
Published: (2024)

Multitask Learning for Earth Observation Data Classification with Hybrid Quantum Network
by: Fan, Fan, et al.
Published: (2026)

Modeling Multi-Task Model Merging as Adaptive Projective Gradient Descent
by: Wei, Yongxian, et al.
Published: (2025)

Gradient-Weight Alignment as a Train-Time Proxy for Generalization in Classification Tasks
by: Hölzl, Florian A., et al.
Published: (2025)

Offline Multitask Representation Learning for Reinforcement Learning
by: Ishfaq, Haque, et al.
Published: (2024)

Relaxed Equivariance via Multitask Learning
by: Elhag, Ahmed A., et al.
Published: (2024)

Gradient Weight-normalized Low-rank Projection for Efficient LLM Training
by: Huang, Jia-Hong, et al.
Published: (2024)

Multitask Learning with Stochastic Interpolants
by: Negrel, Hugo, et al.
Published: (2025)

Multitask Online Learning: Listen to the Neighborhood Buzz
by: Achddou, Juliette, et al.
Published: (2023)

How to Weight Multitask Finetuning? Fast Previews via Bayesian Model-Merging
by: Maldonado, Hugo Monzón, et al.
Published: (2024)

Recency-Weighted Temporally-Segmented Ensemble for Time-Series Modeling
by: Johnsen, Pål V., et al.
Published: (2024)

Multitask Learning Can Improve Worst-Group Outcomes
by: Kulkarni, Atharva, et al.
Published: (2023)