DMTG groups tasks for multi-task learning in one shot.
problem Efficiently grouping and training multiple tasks in machine learning.
method Formulates Multi-Task Grouping as a differentiable pruning problem, training all groups simultaneously.
result Significantly improves training efficiency and mitigates objective bias.
SON-GOKU uses graph coloring to improve multi-task learning by partitioning tasks into compatible groups.
problem Gradient interference between conflicting multi-task learning objectives slows convergence and model performance.
method SON-GOKU computes gradient interference, constructs an interference graph, and applies greedy graph-coloring to partition tasks.
result SON-GOKU consistently outperforms baselines and state-of-the-art multi-task optimizers on six datasets.
Sparse mapping has been a key methodology in many high-dimensional scientific problems. When multiple tasks share the set of relevant features, learning them jointly in a group drastically improves the quality of relevant feature selection. However, in practice this technique is used limitedly since such grouping infor…
The paper improves multi-task learning by selecting variables and grouping tasks.
problem Improving generalization performance in multi-task learning.
method Factorizes a coefficient matrix into two matrices with sparsity for variable selection and overlapping group structure among tasks. Minimized using alternating optimization methods.
result Validated the effectiveness of the method on both synthetic and real-world datasets.
This paper considers the multi-task learning problem and in the setting where some relevant features could be shared across few related tasks. Most of the existing methods assume the extent to which the given tasks are related or share a common feature space to be known apriori. In real-world applications however, it i…
CondMTL improves toxicity detection by learning group-specific representations.
problem Algorithmic bias in toxic language detection across demographic groups.
method Conditional Multi-Task Learning (CondMTL) for demographic-specific tasks.
result CondMTL improves predictive recall for minority demographic groups.
In the paradigm of multi-task learning, mul- tiple related prediction tasks are learned jointly, sharing information across the tasks. We propose a framework for multi-task learn- ing that enables one to selectively share the information across the tasks. We assume that each task parameter vector is a linear combi- nat…
Framework discovers patient subgroups for better multi-task ICU mortality prediction.
problem Predicting adverse outcomes in heterogeneous ICU patient populations.
method Two-step framework: 1) Unsupervised autoencoder for subgroup discovery, 2) Multi-task learning for separate patient populations.
result Better predictive performance of in-hospital mortality across and within patient groups.
Gen AI improves document understanding but not data analysis in public sector tasks.
problem Understanding the impact of Gen AI on public sector tasks.
method Pre-registered field experiment comparing Gen AI to control group performance.
result Mixed results: Gen AI improves document understanding but not data analysis.
Scalable multi-task regression via sparse Gaussian process priors.
problem Efficiently modeling and predicting multiple related tasks.
method Direct Cholesky factorization for sparse parameterization of Gaussian process priors.
result Sparse parameterization improves scalability and accuracy in multi-task regression.
Improves model calibration and selection in unsupervised domain adaptation.
problem Distribution shifts in unsupervised domain adaptation.
method Developed a novel importance weighted group accuracy estimator.
result Improves state-of-the-art performances by 22% in model calibration and 14% in model selection.
REFIL learns from imagined sub-group interactions to improve multi-agent reinforcement learning.
problem Learning efficiency in multi-agent reinforcement learning settings.
method Randomized Entity-wise Factorization (REFIL) approach.
result REFIL outperforms all strong baselines in challenging multi-task StarCraft settings.
Deep networks learn hierarchical data by invariant representations.
problem How many examples are needed for deep networks to learn hierarchical data?
method Random Hierarchy Model: synthetic tasks inspired by language and images hierarchy.
result Deep networks learn by invariant representations and require a detectable number of correlations between low-level features and classes.
EquivCNP learns group symmetries for conditional data.
problem Learning conditional models with data symmetries.
method Group equivariant decomposition and Lie group convolutional layers.
result EquivCNP achieves comparable performance and zero-shot generalization.
Since learning is typically very slow in Boltzmann machines, there is a need to restrict connections within hidden layers. However, the resulting states of hidden units exhibit statistical dependencies. Based on this observation, we propose using l1/l2 regularization upon the activation possibilities of hidden unit…
EDGI improves sample efficiency and generalization in tasks with spatial and temporal symmetries.
problem Sample inefficiency and poor generalization in tasks with geometric symmetries.
method Equivariant Diffuser framework, SE(3)xZxSn-equivariant diffusion model.
result EDGI is more sample efficient and generalizes better than non-equivariant models.
LieTransformer extends self-attention to Lie groups for improved deep learning tasks.
problem Improving deep learning performance through group equivariant self-attention.
method LieSelfAttention layers that are equivariant to arbitrary Lie groups and their discrete subgroups.
result Competitive experimental results on various tasks.
Safe screening rule reduces computational costs for Group OWL models.
problem High computational costs and memory usage in solving Group OWL models.
method Safe screening rule for Group OWL models that identifies and removes inactive features.
result Significant computational gain and memory savings achieved without loss of accuracy.
MTLRRC improves MTL by robustly clustering tasks and detecting outliers.
problem Improving MTL by handling outlier tasks and sharing common information.
method Robust regularized clustering with non-convex group penalties.
result MTLRRC effectively detects and clusters tasks, improving overall performance.
Framework quantifies semantic similarity between groups of embeddings.
problem Quantifying semantic similarity between groups of embeddings.
method Formulates model comparison task, contrasts generative models, uses information criteria.
result Achieves competitive results in Semantic Textual Similarity tasks.
A new method for multi-task learning infers task hierarchies from data.
problem Inferring predictive maps between multiple tasks in plant genetics.
method Task clustering for sparse linear regression models.
result Superior predictive models and genetic mapping from remote sensing data.
AGS-CL selectively updates penalties based on node importance for continual learning.
problem Catastrophic forgetting in continual learning.
method Adaptive Group Sparsity (AGS) with proximal gradient descent.
result Significantly outperforms baselines on various continual learning benchmarks.
Neural clustering learns to group and represent entities.
problem Automated discovery of distributed symbol-like representations for reasoning and interaction.
method Formalizes the problem as spatial mixture model with neural network parameters, derives differentiable Expectation Maximization clustering method.
result Successfully learns to group and represent individual entities in a sequential perceptual grouping task.
Contrastive learning harms minority group representations, affecting downstream tasks.
problem Representation harm in contrastive learning, especially affecting minority groups.
method Causal mediation analysis and stochastic block model explanation.
result Representation harm in contrastive learning is partly responsible for allocation harm in downstream tasks.
Paper defines and solves a problem in representation learning to ensure fairness with high confidence.
problem Learning fair representations with high confidence guarantees for all downstream tasks.
method Formally defines the problem, introduces FRG framework, proves high probability fairness, and demonstrates effectiveness empirically.
result FRG framework provides high-confidence guarantees for limiting unfairness across all downstream models and tasks.
Personalized models using group attributes reduce performance, study finds.
problem Reducing performance of models using group attributes like race or gender.
method Formal conditions and collective preference guarantees to ensure fair use.
result Models personalized with group attributes reduce performance at a group level.
Proposes an MTL method with clustering to improve regression accuracy.
problem Improving regression accuracy by sharing information among related tasks.
method Centroid parameter for clustering tasks, separating regression and clustering parameters.
result Improves estimation and prediction accuracy for regression coefficient vectors.
Transfer learning artist group factors for more accurate music genre classification.
problem Automated music genre classification from audio is challenging due to subjective and noisy genre labels.
method Apply transfer learning to learn artist-related factors for genre classification, using different transfer methods.
result Achieved highest validation accuracy on FMA dataset through multi-task learning.
Group equivariant neural networks simplify complex tasks with group representation theory.
problem Challenging tasks requiring input transformations like rotations.
method Group representation theory, non-commutative harmonic analysis, differential geometry.
result A neural network is group equivariant if and only if it has a convolutional structure.
This paper introduces a method to select and weight pretext tasks for better self-supervised speech representation learning.
problem Combining pretext tasks for better performance in self-supervised speech representation learning.
method Estimating calibrated weights for partial losses corresponding to pretext tasks during self-supervised training.
result Groups of selected and weighted pretext tasks perform better than classic baselines in automatic speech recognition and speaker/emotion recognition.
GSA-Nets apply group equivariance to self-attention for vision tasks.
problem Improving self-attention networks for vision tasks.
method Define group-equivariant positional encodings.
result GSA-Nets outperform non-equivariant self-attention networks on vision benchmarks.
Study on when the lower central series stops for various groups, including braid groups.
problem Understanding when the lower central series stops for different groups.
method Various techniques applied to braid groups and related groups.
result Complete computation of the lower central series for most groups studied.
Enhances student diversity in collaborative learning.
problem Student homogenization in large groups.
method Random routing, diverse feature sets, and random subgroup imitation.
result Significantly outperforms state-of-the-art approaches.
Paper proposes a new method to protect model information in multi-task learning.
problem Protecting model information in multi-task learning from adversaries.
method Proposes a privacy-preserving MTL framework using perturbation of the covariance matrix.
result Our algorithms outperform existing privacy-preserving MTL methods and STL methods.
Improved neural networks by combining group DRO with regularization.
problem Overparameterized neural networks can fail on atypical groups due to spurious correlations.
method Coupling distributionally robust optimization (DRO) with increased regularization.
result Significant improvements in worst-case group accuracy, maintaining high average accuracy.
Proposes TFCL to mitigate negative transfer in MTL by collaborating across features and tasks.
problem Negative transfer in Multi-Task Learning (MTL) due to dissimilar tasks.
method Task-Feature Collaborative Learning (TFCL) with heterogeneous block-diagonal structure regularizer and optimization method.
result Global convergence and block-diagonal structure recovery guarantees.
Multitask learning can be effective when features useful in one task are also useful for other tasks, and the group lasso is a standard method for selecting a common subset of features. In this paper, we are interested in a less restrictive form of multitask learning, wherein (1) the available features can be organized…
Joint sparsity regularization in multi-task learning has attracted much attention in recent years. The traditional convex formulation employs the group Lasso relaxation to achieve joint sparsity across tasks. Although this approach leads to a simple convex formulation, it suffers from several issues due to the loosenes…
Method compares sentences by cosine similarity of vector projections.
problem Measuring semantic similarity of sentences.
method Cosine similarity of vector projections of sentence groups.
result Advantages over existing methods in preserving word order and syntactic connections.
Multi-task learning leverages shared information among data sets to improve the learning performance of individual tasks. The paper applies this framework for data where each task is a phase-shifted periodic time series. In particular, we develop a novel Bayesian nonparametric model capturing a mixture of Gaussian proc…
Transformer models waste resources on long-context tasks.
problem Redundant attention computations in Transformer models for long-context tasks.
method Reformulate sequence modeling as supervised learning, analyze attention sparsity, formulate attention optimization as linear coding problem, propose Dynamic Group Attention.
result DGA reduces computational costs while maintaining performance.
Multi-task learning models using Gaussian processes (GP) have been developed and successfully applied in various applications. The main difficulty with this approach is the computational cost of inference using the union of examples from all tasks. Therefore sparse solutions, that avoid using the entire data directly a…
New approach for multi-task reinforcement learning without task interference.
problem Efficient knowledge sharing between tasks in reinforcement learning.
method Attention-based multi-task deep reinforcement learning.
result Achieves positive knowledge transfer and avoids negative transfer.
NS-RGS improves orthogonal group synchronization with faster convergence.
problem Orthogonal group synchronization from pairwise measurements.
method Newton-Schulz iteration for Riemannian gradient optimization.
result NS-RGS achieves linear convergence and near-optimal accuracy.
A new multi-task learning estimator improves Gaussian graphical regression model fitting.
problem High error rate in fitting Gaussian graphical regression models due to separate node-wise lasso regressions.
method Proposes a multi-task learning estimator with cross-task group sparsity and within-task element-wise sparsity penalties, solved via an efficient augmented Lagrangian algorithm.
result Error rate improvement over separate node-wise lasso estimates, demonstrated through simulations and application to gene co-expression network study.
Proposes Group Loss for deep metric learning to improve clustering and image retrieval.
problem Improving deep metric learning for better clustering and image retrieval.
method Group Loss based on label-propagation method enforcing embedding similarity across all samples of a group.
result Shows state-of-the-art results on clustering and image retrieval on several datasets.
Proposes a novel MTL approach based on bias-variance analysis.
problem Improving multi-task learning performance through shared knowledge.
method Two-phase iterative aggregation of targets and features using bias-variance analysis.
result Validation on synthetic and real-world datasets demonstrates the effectiveness of the proposed method.
Unified understanding of neural networks on group operations verified.
problem Understanding and verifying neural networks trained on group operations.
method Investigated one-hidden-layer neural networks trained on binary operation of finite groups, revealing structure and providing a compact proof of model performance.
result Verified explanation applies to a large fraction of networks trained on the symmetric group S5, providing a >=95% accuracy bound for 45% of models.