This paper reviews dMTL and methods for selecting auxiliary tasks.
problem Improving model performance for multiple tasks.
method Review of dMTL approaches and methods for selecting auxiliary tasks.
result Methods for selecting auxiliary tasks can improve dMTL performance.
New method for learning evolving tasks with performance guarantees.
problem Learning tasks in a sequence with evolving similarity.
method Adaptable learning methodology with performance guarantees.
result Improved performance in multiple scenarios with reliable guarantees.
Deep multitask learning boosts performance by sharing learned structure across related tasks. This paper adapts ideas from deep multitask learning to the setting where only a single task is available. The method is formalized as pseudo-task augmentation, in which models are trained with multiple decoders for each task.…
Optimal task order improves continual learning performance.
problem Challenges in neural networks learning multiple tasks in sequence.
method Linear teacher-student model with latent factors, derived analytical expression.
result Two principles for optimal task order: least representative first and dissimilar adjacent tasks.
Paper proposes a method to identify negative transfers in multitask learning using surrogate models.
problem Identifying subsets of source tasks that improve target task performance in multitask learning.
method Surrogate modeling to precompute multitask learning performances and approximate them with a linear regression model.
result The approach predicts negative transfers from multiple source tasks to target tasks more accurately than existing methods.
A TS algorithm improves performance in multi-task bandits with transfer.
problem Improving performance across multiple related bandit tasks.
method A TS-type algorithm for online multi-task learning with a novel concentration inequality.
result The TS-type algorithm achieves nearly-optimal performance guarantees.
Recent advances in reinforcement learning have proved that given an environment we can learn to perform a task in that environment if we have access to some form of a reward function (dense, sparse or derived from IRL). But most of the algorithms focus on learning a single best policy to perform a given set of tasks. I…
A simple approach improves performance on both past and future tasks in lifelong learning.
problem Forgetting in lifelong learning, where performance on past tasks degrades when learning new tasks.
method Representation ensembling to improve performance on both future and past tasks.
result Representation ensembling demonstrates both forward and backward transfer across various datasets.
Paper presents IMRCs for evolving tasks with forward and backward learning.
problem Incremental learning of evolving tasks with few samples per task.
method Incremental minimax risk classifiers (IMRCs) that exploit forward and backward learning.
result IMRCs provide significant performance improvement, especially with reduced sample sizes.
Study on multitask learning performance factors.
problem Mixed results in multitask learning performance.
method Task simulator and symbolic regression to learn performance factors.
result Empirical formulas relating model performance to sqrt(n), sqrt(T), and sqrt(AMI).
Multi-task learning (MTL) has recently contributed to learning better representations in service of various NLP tasks. MTL aims at improving the performance of a primary task, by jointly training on a secondary task. This paper introduces automated tasks, which exploit the sequential nature of the input data, as second…
Sharing information between multiple tasks enables algorithms to achieve good generalization performance even from small amounts of training data. However, in a realistic scenario of multi-task learning not all tasks are equally related to each other, hence it could be advantageous to transfer information only between …
HydaLearn dynamically adjusts task weights for better MTL performance.
problem Constant loss weights in MTL lead to poor results due to drifting relevance and varying mini-batch composition.
method HydaLearn uses mini-batch gradients to dynamically adjust task weights.
result HydaLearn improves performance on synthetic and real-world data.
New method improves meta-learning performance by task-specific initialization.
problem Difficulties in generalizing and achieving theoretical guarantees in conditional meta-learning.
method Structured prediction approach for task-specific initialization.
result TASML improves performance of existing meta-learning models.
COCOA can learn new tasks without forgetting previously learned ones in a distributed setting.
problem Continual learning with tasks arriving sequentially.
method Distributed optimization with COCOA algorithm.
result COCOA can perform continual learning without forgetting.
Enhances cooperative multi-task SemCom for distributed users.
problem Performance degradation in cooperative multi-tasking due to negative information transfer.
method Federated learning (FL) with semantic-aware task clustering.
result Constructive cooperation across distributed users with semantic-aware task clustering.
The reinforcement learning community has made great strides in designing algorithms capable of exceeding human performance on specific tasks. These algorithms are mostly trained one task at the time, each new task requiring to train a brand new agent instance. This means the learning algorithm is general, but each solu…
Sequential learning of multiple tasks in artificial neural networks using gradient descent leads to catastrophic forgetting, whereby previously learned knowledge is erased during learning of new, disjoint knowledge. Here, we propose a new approach to sequential learning which leverages the recent discovery of adversari…
Neural architecture search has been shown to hold great promise towards the automation of deep learning. However in spite of its potential, neural architecture search remains quite costly. To this point, we propose a novel gradient-based framework for efficient architecture search by sharing information across several …
Proposes a method to evaluate meta-learning performance based on task similarity.
problem Meta-learning performance evaluation ignores task similarity, leading to biased results.
method Generative approach using Latent Dirichlet Allocation to analyze task similarity.
result The proposed method provides an insightful evaluation of meta-learning algorithms, matching common intuition.
Knowledge transfer between tasks can improve the performance of learned models, but requires an accurate estimate of the inter-task relationships to identify the relevant knowledge to transfer. These inter-task relationships are typically estimated based on training data for each task, which is inefficient in lifelong …
Trained recurrent networks are powerful tools for modeling dynamic neural computations. We present a target-based method for modifying the full connectivity matrix of a recurrent network to train it to perform tasks involving temporally complex input/output transformations. The method introduces a second network during…
GTI network learns linguistic features for multi-task sequence tagging.
problem Improving neural model performance on multi-task sequence tagging without explicit features.
method GTI network with neural gate modules to learn relations between tasks.
result GTI network outperforms baselines on chunking and NER tasks.
A new method for multi-task learning improves performance without weakening inductive bias.
problem Joint optimization of parameters for multiple tasks remains challenging.
method Maximum Roaming, a novel parameter partitioning method inspired by dropout.
result Maximum Roaming improves performance compared to recent multi-task learning formulations.
Overparameterized models improve performance in sequential learning tasks.
problem Catastrophic forgetting in overparameterized neural networks.
method Two-task linear regression problem with random orthogonal transformations.
result Overparameterization mitigates catastrophic forgetting in sequential learning tasks.
BI-MAML learns multiple tasks without forgetting old ones.
problem Catastrophic forgetting in meta learning.
method Incremental model adaptation with balanced learning strategy.
result BI-MAML outperforms state-of-the-art models in accuracy and efficiency.
TAAN model learns optimal network architecture for MTL tasks.
problem Improving generalization performance of MTL by finding flexible and accurate shared architecture.
method TAAN model with flexible activation functions and functional regularization.
result TAAN and regularization methods improve MTL performance.
A ranking network improves neural architecture search efficiency.
problem Efficiently search for neural network architectures without extensive training.
method Pairwise ranking loss for a performance predictor trained on task meta-features.
result The ranking network outperforms the performance predictor in architecture search.
MBML improves multi-task RL by inferring task identity from state-action pairs.
problem Multi-task batch reinforcement learning with unseen tasks.
method MBML uses triplet loss and relabeling to robustify task inference.
result Significantly faster convergence on unseen tasks compared to random initialization.
The paper tackles learning from similar but not identical linear representations, improving performance over single-task learning.
problem Understanding how to learn from tasks with similar but not exactly the same linear representations, especially when dealing with outlier tasks.
method Proposes adaptive and robust penalized empirical risk minimization and spectral methods.
result Both methods outperform single-task learning when representations are similar and perform at least as well otherwise, with minimax optimality demonstrated.
FedGradNorm improves federated MTL by balancing task learning speeds.
problem Statistical and data heterogeneity in federated MTL.
method Dynamic-weighting normalization of gradient norms.
result FedGradNorm achieves faster training performance and balanced datasets.
HyperSTAR optimizes deep network hyperparameters for specific tasks.
problem Finding optimal hyperparameters for deep neural networks is computationally expensive and task-agnostic approaches are inefficient.
method HyperSTAR learns a dataset representation and a performance predictor from raw images, ranking and recommending hyperparameters conditioned on a joint dataset-hyperparameter space.
result HyperSTAR reduces HPO time by 50% on large-scale image classification datasets.
We consider multi-task learning, which simultaneously learns related prediction tasks, to improve generalization performance. We factorize a coefficient matrix as the product of two matrices based on a low-rank assumption. These matrices have sparsities to simultaneously perform variable selection and learn and overlap…
Many advanced Learning from Demonstration (LfD) methods consider the decomposition of complex, real-world tasks into simpler sub-tasks. By reusing the corresponding sub-policies within and between tasks, they provide training data for each policy from different high-level tasks and compose them to perform novel ones. E…
Multi-task learning aims to learn multiple tasks jointly by exploiting their relatedness to improve the generalization performance for each task. Traditionally, to perform multi-task learning, one needs to centralize data from all the tasks to a single machine. However, in many real-world applications, data of differen…
Gradient-based meta-RL fails with incorrect task distributions, leading to instability and poor performance.
problem Gradient-based meta-RL's sensitivity to task distributions causes instability and poor performance.
method Proposes meta Active Domain Randomization (meta-ADR) to learn task distributions for gradient-based meta-RL.
result Meta-ADR improves stability and generalization of MAML on simulated locomotion and navigation tasks.
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.
New MAML variant prioritizes hardest tasks, improving robustness.
problem Meta-learning's focus on average performance, ignoring worst-case.
method Reformulate MAML to minimize max loss over observed tasks.
result Task-robust model performs well across various task distributions.
Meta-learning shows negative transfer between tasks, which MetaCRL addresses.
problem Negative transfer between tasks in meta-learning.
method Structural Causal Models (SCMs) and MetaCRL to eliminate task confounders.
result MetaCRL achieves state-of-the-art performance in various benchmark datasets.
Multi-task learning is a method for improving the generalizability of multiple tasks. In order to perform multiple classification tasks with one neural network model, the losses of each task should be combined. Previous studies have mostly focused on multiple prediction tasks using joint loss with static weights for tr…
Novel model improves clinical risk prediction by transferring knowledge between tasks over time.
problem Negative transfer in multi-task learning for clinical risk prediction.
method Temporal Probabilistic Asymmetric Multi-Task Learning (TPAMTL).
result Significantly outperforms various deep learning models for time-series prediction.
Neural networks learn symbolic structure to perform compositional tasks.
problem How neural networks perform well on compositional tasks without explicit representations.
method ROLE analysis to uncover symbolic structure in recurrent neural networks.
result Neural networks converge to solutions that implicitly represent symbolic structure.
Sharing knowledge between tasks is vital for efficient learning in a multi-task setting. However, most research so far has focused on the easier case where knowledge transfer is not harmful, i.e., where knowledge from one task cannot negatively impact the performance on another task. In contrast, we present an approach…
MTL-NAS combines NAS with GP-MTL for task-agnostic multi-task learning.
problem Designing architectures for diverse tasks with varying priors.
method Disentangled GP-MTL networks, hierarchical feature sharing, and gradient-based search.
result General-purpose model trained once can adapt to multiple tasks.
Gradient-based meta-learning methods leverage gradient descent to learn the commonalities among various tasks. While previous such methods have been successful in meta-learning tasks, they resort to simple gradient descent during meta-testing. Our primary contribution is the {\em MT-net}, which enables the meta-learner…
LEWIS merges LLMs without training, improving performance on specific tasks.
problem Limited performance improvement of merged models on specific benchmarks.
method Guided model merging using layer-wise sparsity and task-vector pruning.
result Improved model performance by up to 11.3% on math-solving tasks.
Meta-learning performance is affected by how task diversity is allocated, not just overall variability.
problem Meta-learning performance degrades when task diversity is unevenly distributed.
method Decomposed task-specific regression effects into structurally informative and orthogonal components.
result Meta-learning prediction degrades when a larger fraction of task variability is orthogonal and non-informative.
Curriculum learning in reinforcement learning is used to shape exploration by presenting the agent with increasingly complex tasks. The idea of curriculum learning has been largely applied in both animal training and pedagogy. In reinforcement learning, all previous task sequencing methods have shaped exploration with …