REVIEW 16 cited by
Multi-Task Learning with Deep Neural Networks: A Survey
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
Multi-task learning (MTL) is a subfield of machine learning in which multiple tasks are simultaneously learned by a shared model. Such approaches offer advantages like improved data efficiency, reduced overfitting through shared representations, and fast learning by leveraging auxiliary information. However, the simultaneous learning of multiple tasks presents new design and optimization challenges, and choosing which tasks should be learned jointly is in itself a non-trivial problem. In this survey, we give an overview of multi-task learning methods for deep neural networks, with the aim of summarizing both the well-established and most recent directions within the field. Our discussion is structured according to a partition of the existing deep MTL techniques into three groups: architectures, optimization methods, and task relationship learning. We also provide a summary of common multi-task benchmarks.
Forward citations
Cited by 16 Pith papers
-
Co-Adaptive Multi-Task LoRA: Transfer-Aware, Label-Free Control of Domain Participation
A forward-only controller sets multi-domain LoRA participation from label-free competence and cross-domain affinity, improving average accuracy while using half the data.
-
LoMeVQA: A Comprehensive Benchmark for Longitudinal Medical VQA
A 206K multi-task longitudinal medical VQA benchmark shows current MLLMs fail at temporal reasoning, while fine-tuned MedLong-8B sets a strong baseline.
-
Asymptotic Behavior of Multi--Task Learning: Implicit Regularization and Double Descent Effects
Multi-task learning of related perceptrons is asymptotically a single-task problem plus explicit regularizers that improve generalization and postpone double descent.
-
MultiPUFFIN: A Multimodal Domain-Constrained Foundation Model for Molecular Property Prediction of Small Molecules
MultiPUFFIN claims higher test R² than ChemBERTa-2 on all nine thermophysical properties while using far fewer labeled molecules, with the largest gains on temperature-dependent properties.
-
Developer-LLM Conversations: An Empirical Study of Interactions and Generated Code Quality
Analyzing 82,845 real ChatGPT coding chats shows generated code frequently has language-specific issues, with some quality problems persisting or worsening over multiple turns.
-
Relativistic Quantum Thermal Machine: Harnessing Relativistic Effects to Surpass Carnot Efficiency
Relativistic motion of the reservoirs in a three-level maser is claimed to yield a generalized Carnot bound that allows efficiency above the ordinary Carnot limit.
-
Separating Shared and Domain-Specific LoRAs for Multi-Domain Learning
Shared and domain-specific LoRAs are constrained to the column and left null spaces of pretrained weights, but experimental benefits are mixed.
-
A High Magnifications Histopathology Image Dataset for Oral Squamous Cell Carcinoma Diagnosis and Prognosis
Multi-OSCC is a public dataset linking six high-magnification pathology images per oral cancer patient to six diagnostic and prognostic labels, with benchmark results showing pathology-pretrained models and task-speci...
-
Efficient and Scalable Estimation of Distributional Treatment Effects with Multi-Task Neural Networks
A multi-task neural network with monotonic cumulative-distribution outputs estimates distributional treatment effects faster and with lower variance than single-task regression adjustment.
-
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.
-
VAIOM: Continuous-Input, Discrete-Output Decoder-Only Financial Sequence Modeling
A continuous-input, categorical-output decoder-only Transformer improves held-out one-hour FX return likelihood over single-bar LightGBM and statistical baselines.
-
Modular Foundation Models for Time-Series Perception in Digital Twins
A gated bank of frozen self-supervised time-series encoders, aligned and aggregated by a Transformer, supports competitive multi-task perception for digital twins and hydro-generator virtual sensing.
-
SAMO: A Lightweight Sharpness-Aware Approach for Multi-Task Optimization with Joint Global-Local Perturbation
SAMO jointly uses global and local perturbations with forward-only task gradient approximation to improve multi-task learning performance at lower cost than F-MTL.
-
OmniVec2 -- A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning
A shared-backbone transformer with pairwise modality training reports top results across 25 datasets spanning 12 modalities.
-
Learning to Collaborate Over Graphs: A Selective Federated Multi-Task Learning Approach
SFMTL-Graph builds a dynamic client similarity graph, partitions it with Louvain community detection, and restricts federated model aggregation to within communities to personalize learning while cutting communication.
-
Beyond Hard Sharing: Efficient Multi-Task Speech-to-Text Modeling with Supervised Mixture of Experts
A supervised mixture of experts, routed by fixed bandwidth and task labels, improves multi-task ASR/ST over hard parameter sharing while keeping active parameters constant.
Discussion (0). Sign in to comment.