REVIEW 14 cited by
Multi-Task Learning as a Bargaining Game
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
In Multi-task learning (MTL), a joint model is trained to simultaneously make predictions for several tasks. Joint training reduces computation costs and improves data efficiency; however, since the gradients of these different tasks may conflict, training a joint model for MTL often yields lower performance than its corresponding single-task counterparts. A common method for alleviating this issue is to combine per-task gradients into a joint update direction using a particular heuristic. In this paper, we propose viewing the gradients combination step as a bargaining game, where tasks negotiate to reach an agreement on a joint direction of parameter update. Under certain assumptions, the bargaining problem has a unique solution, known as the Nash Bargaining Solution, which we propose to use as a principled approach to multi-task learning. We describe a new MTL optimization procedure, Nash-MTL, and derive theoretical guarantees for its convergence. Empirically, we show that Nash-MTL achieves state-of-the-art results on multiple MTL benchmarks in various domains.
Forward citations
Cited by 14 Pith papers
-
DanceOPD: On-Policy Generative Field Distillation
Hard-routed, single low-noise on-policy velocity matching composes conflicting image-generation capabilities into one flow student better than joint training, merging, or dense OPD baselines.
-
S2T-RLHF: Hierarchical Credit Assignment for Stable Preference-Based RLHF
S2T-RLHF splits each response-level RLHF reward into sentence shares and then token shares, via bargaining and Dirichlet weighting, yielding steadier training with competitive preference alignment.
-
GreenRFM: Learning a resource-efficient radiology vision-language foundation model via supervision-centric pre-training
MUST supervision—LLM-distilled diagnostic labels plus two-stage ubiquitous training—lets a 33M-parameter 3D ResNet-18 reach 84.8 zero-shot AUC on CT-RATE in 24 GPU-hours and transfer across institutions and MRI.
-
Simple Optimizers for Convex Aligned Multi-Objective Optimization
Convex AMOO is analyzed under Lipschitz and smooth assumptions with a maximum-gap metric, giving simple gradient methods with rates independent of the number of objectives, plus a flawed equal-weights lower bound.
-
AutoScale: Linear Scalarization Guided by Multi-Task Optimization Metrics
AutoScale selects fixed linear-scalarization weights by optimizing multi-task optimization metrics during a short exploration phase, matching grid-searched performance without search.
-
Synchronizing Task Behavior: Aligning Multiple Tasks during Test-Time Training
S4T synchronizes multi-task test-time adaptation by learning cross-task relations on the source domain and using them to align task predictions on the target domain.
-
Resolving Token-Space Gradient Conflicts: Token Space Manipulation for Transformer-Based Multi-Task Learning
A token-space SVD-based method that separately resolves gradient conflicts in the range and null spaces of transformer tokens improves multi-task learning performance with minimal extra parameters.
-
Interaction-Merged Motion Planning: Effectively Leveraging Diverse Motion Datasets for Robust Planning
A two-step model-merging method transfers interaction knowledge from multiple motion datasets to a target domain, outperforming ensembling and domain adaptation at the same inference cost.
-
FastCAR: Fast Classification And Regression for Task Consolidation in Multi-Task Learning to Model a Continuous Property Variable of Detected Object Class
A single regression network trained on class-shifted hardness labels can jointly classify steel microstructures and predict hardness, outperforming multi-task baselines on the authors' own dataset.
-
GRAPE: Optimize Data Mixture for Group Robust Multi-target Adaptive Pretraining
GRAPE uses a minimax group-DRO scheme to reweight both source domains and target tasks during pretraining, improving multi-task reasoning and low-resource language modeling.
-
FairHuman: Boosting Hand and Face Quality in Human Image Generation with Minimum Potential Delay Fairness in Diffusion Models
A multi-objective fine-tuning method with Minimum Potential Delay fairness improves hand and face quality in human image generation while maintaining global quality.
-
MINT: Multimodal Instruction Tuning with Multimodal Interaction Grouping
Grouping instruction-tuning datasets by redundancy, uniqueness, or synergy of text-image interaction improves vision-language model accuracy over single-task and unselective multi-task tuning.
-
AutoMixAlign: Adaptive Data Mixing for Multi-Task Preference Optimization in LLMs
AutoMixAlign adaptively reweights or resamples task data during DPO training to match specialist-model losses, improving average performance on helpfulness, coding, and safety benchmarks compared to standard DPO and m...
-
Expert Merging in Sparse Mixture of Experts with Nash Bargaining
Expert merging in MoE models can be improved by setting per-expert weights with the Nash bargaining solution instead of simple averaging.
Discussion (0). Continue with ORCID to comment.