Low-rank framework for task-specific LLM ranking from sparse comparisons.
problem Challenges in reliable task-specific ranking of LLMs under sparse, imbalanced comparisons.
method Low-rank modeling of task-by-model ability matrix, max-norm accurate estimator, task-wise top-K recovery guarantees, uncertainty quantification framework.
result Improves sample efficiency and produces tighter, better-calibrated ranking certificates.
Meta-learning approach discovers task-specific modules for few-shot tasks.
problem Meta-learning large models with limited task-specific data.
method Bayesian shrinkage for automatic discovery of task-specific and general modules.
result Outperforms existing meta-learning methods in domains with little task data and long adaptation horizons.
Enhances index selection for databases with task-specific inductive biases.
problem Challenges in traditional and automatic tuning strategies for database index set selection.
method Applies deep RL with task-specific inductive biases to index set selection, reformulating the problem as permutation learning.
result Improves index selection, achieving up to 40% smaller configurations with similar latency.
Algorithm learns which weights to share in deep multi-task learning.
problem Difficulty in deciding which weights to share between tasks in deep learning models.
method Combines natural evolution strategy and stochastic gradient descent to learn optimal weight sharing.
result Task-specific networks achieve lower test errors than existing methods on multi-task learning datasets.
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.
Unified MTL framework for heterogeneous data integrates shared and task-specific encoders.
problem Efficiently sharing information across multiple tasks with heterogeneous data.
method Dual-encoder framework with task-shared and task-specific encoders.
result Unified algorithm alternates learning task-specific and shared encoders and coefficients.
Method selects task-specific neurons for unsupervised transfer learning.
problem Challenges in fine-tuning large language models for specific tasks.
method Selects important neurons for a specific classification task and extends to multi-source transfer learning.
result Higher similarity between task-specific fingerprints leads to better transferability.
Meta-RL learns shared and task-specific information for quick adaptation.
problem Data inefficiency and limited generalization in deep RL.
method Task embedding and shared policy learned via SGD meta-learner.
result 3 to 4 times higher returns on novel tasks compared to baselines.
This research improves multitask learning by creating task-specific pathways.
problem Creating task-specific representations for efficient learning.
method Developed generalization bounds for learning multiple tasks over multiple pathways.
result Proves the superiority of multipath representation over traditional shallow supernets.
Few-shot Learning aims to learn classifiers for new classes with only a few training examples per class. Existing meta-learning or metric-learning based few-shot learning approaches are limited in handling diverse domains with various number of labels. The meta-learning approaches train a meta learner to predict weight…
A tensor model for meta-learning adapts to task-specific features.
problem Learning shared representations for diverse tasks without task-specific observable information.
method Modeling meta-parameters as an order-3 tensor, estimating through tensor regression and method of moments.
result Tensor-based approach improves meta-learning performance with fewer samples.
UCB-TQL learns from multiple tasks with shared dynamics and adapts to task-specific variations.
problem Transfer reinforcement learning with composite MDPs where tasks share core dynamics but have sparse differences.
method UCB-TQL, a novel transfer RL algorithm for composite MDPs.
result Achieved a regret bound of i l d e O ( e H 5 N ) ilde{O}(\sqrt{eH^5N}) i l d e O ( e H 5 N ) that scales independently of the ambient dimension. The paper tackles learning domain-specific bias by learning many tasks from the same domain.
problem Learning appropriate domain-specific bias in machine learning models.
method Learning many related tasks from the same domain, with a theorem bounding the number of tasks needed.
result The number of examples required per task for good generalization scales like \(O(a + \frac{b}{n})\), where \(O(a)\) is the minimum number of examples per task and \(O(a + b)\) is the number of examples per task independently.
This work improves task specification learning from demonstrations using maximum causal entropy.
problem Lack of guarantees for safe task composition and historical dependencies in learning from demonstrations.
method Adapting maximum causal entropy inverse reinforcement learning to estimate task specifications using reduced ordered binary decision diagrams.
result Polynomial time algorithm for estimating task specifications from demonstrations.
Bayesian framework optimizes 3D view selection for specific tasks.
problem Optimizing 3D view selection for specific tasks in reconstruction.
method Bayesian decision theory, prior and posterior distributions, stochastic surface reconstruction.
result Framework achieves superior performance with fewer views.
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…
AFTER technique improves NLP models by preventing overfitting to task-specific domains.
problem Standard fine-tuning degrades pretraining domain representations.
method Complements task-specific loss with adversarial objective.
result AFTER leads to improved performance on various NLP tasks.
Hybrid framework prevents forgetting in continual learning.
problem Avoiding forgetting in learning new tasks without forgetting old ones.
method Hybrid continual learning framework combining architecture growth and experience replay.
result Hybrid approach effectively avoids forgetting across multiple tasks.
Paper presents a probabilistic framework for diffusion synchronization.
problem Improper application of heuristics leads to suboptimal results in diffusion synchronization.
method Develops a probabilistic framework to analyze and adapt correlation models for each specific task.
result Achieves better results by identifying optimal correlation models per task.
Bayesian TAML balances meta-knowledge and task-specific learning for imbalanced tasks.
problem Meta-learning approaches struggle with varying instance and class numbers and distributional differences.
method Bayesian inference framework with variational inference to adaptively balance meta-knowledge and task-specific learning.
result Bayesian TAML significantly outperforms existing meta-learning approaches on imbalanced datasets.
A language for specifying complex reinforcement learning tasks.
problem Challenges in specifying and shaping reward functions for complex reinforcement learning tasks.
method Proposes a new language and algorithm for automatically generating and shaping reward functions.
result SPECTRL tool outperforms state-of-the-art baselines.
Unified scoring model improves efficiency and performance across multiple tasks.
problem Efficient and resource-efficient automated scoring for diverse tasks.
method Knowledge-distilled multi-task Mixture-of-Experts (MoE) approach.
result Comparable performance to task-specific models with significantly less storage and training resources.
Improves shared encoder representations for better multi-task learning performance.
problem Improving quality of shared encoder representations in multi-task learning.
method Dummy Gradient norm Regularization (DGR) to decrease gradient norm of dummy task-specific predictors.
result DGR improves multi-task prediction performances and superior performance compared to existing methods.
The increasing availability of electrocardiogram (ECG) data has motivated the use of data-driven models for automating various clinical tasks based on ECG data. The development of subject-specific models are limited by the cost and difficulty of obtaining sufficient training data for each individual. The alternative of…
Framework learns portable representations for diverse tasks.
problem Creating task-independent abstract representations for diverse environments.
method Autonomously learns portable representations in egocentric space.
result Portable representations enable task-independent planning and transfer.
BrainSurfCNN predicts task contrasts from resting-state fingerprints, improving accuracy over baseline.
problem Predicting task-evoked activity from resting-state functional connectivity.
method Surface-based convolutional neural network (BrainSurfCNN) with reconstructive-contrastive loss.
result Significantly improved accuracy in predicting task contrasts over baseline.
The paper proposes a learning algorithm that improves adaptability and generalization.
problem Improving adaptability and generalization in learning models.
method Learning to meta-learn by meta-finetuning on related tasks before adapting to specific tasks.
result Learning to meta-learn improves adaptability and generalization across various tasks.
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.
SPARC improves continual learning with minimal memory and computational overhead.
problem Efficient continual learning for deep neural networks.
method Combines task-specific working memories and task-agnostic semantic memory.
result Significantly reduces parameter usage (6% of full-model surrogates) while maintaining performance.
Few-shot learning aims to learn classifiers for new classes with only a few training examples per class. Most existing few-shot learning approaches belong to either metric-based meta-learning or optimization-based meta-learning category, both of which have achieved successes in the simplified " k k k -shot N N N -way" image c…
New method optimizes experimental design for specific applications.
problem Inability to adapt causal inference methods to specific downstream applications.
method Task-specific experimental design and sampling strategies.
result Significantly reduces data requirements for achieving RCT performance.
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.
A distributed algorithm for online multi-task learning reduces communication and runtime costs.
problem Heavy communication and high runtime complexity in online multi-task learning.
method Adaptive primal-dual algorithm that synchronizes data across geographically distributed tasks.
result The proposed algorithm achieves optimal regret and is effective on real-world datasets.
CAM-GAN improves GANs for continual learning with efficient feature map transformations.
problem Efficient continual learning for GANs with reduced parameter growth.
method Designing and leveraging parameter-efficient feature map transformations, including global and task-specific parameters, residual bias, and Fisher information matrix.
result Significantly improved model performance and high-quality samples with fewer parameters.
Deep neural networks have shown promising results for various clinical prediction tasks such as diagnosis, mortality prediction, predicting duration of stay in hospital, etc. However, training deep networks -- such as those based on Recurrent Neural Networks (RNNs) -- requires large labeled data, high computational res…
A new framework for federated continual learning reduces interference and improves performance.
problem Learning from a sequence of tasks with limited data from each client.
method Federated Weighted Inter-client Transfer (FedWeIT) framework.
result FedWeIT significantly outperforms existing methods with reduced communication cost.
Plan2Explore learns new tasks efficiently through self-supervised planning.
problem Challenges in reinforcement learning, especially task-specific learning and sample efficiency.
method Self-supervised exploration and fast adaptation to new tasks through efficient planning.
result Plan2Explore outperforms prior methods in learning new tasks without supervision.
New PAC-Bayes meta-learning method improves few-shot learning accuracy and calibration.
problem Few-shot learning with limited data.
method PAC-Bayes framework extended to meta-learning, estimating task-specific posteriors.
result State-of-the-art calibration and classification results on benchmarks.
Current deep learning based text classification methods are limited by their ability to achieve fast learning and generalization when the data is scarce. We address this problem by integrating a meta-learning procedure that uses the knowledge learned across many tasks as an inductive bias towards better natural languag…
Graph Denoising Policy Network learns robust representations from noisy graphs.
problem Noise sensitivity in graph representation learning.
method Reinforcement learning to select signal neighborhoods and aggregate features.
result Significantly outperforms state-of-the-art methods on node classification tasks.
HIDRA optimizes weights for diverse tasks, improving model performance.
problem Optimizing gradient-based optimization strategies with dynamic target variables.
method Meta-learning approach that learns a master neuron to initialize output neurons for any number of target variables.
result Improves model performance and generalizes to tasks with any number of target variables.
BNN learns shared features between two data sources for specific tasks.
problem Learning shared features between two data sources for specific tasks.
method BNN uses two CNNs to project data sources into a feature space and learns a common representation for each task.
result BNN achieves state-of-the-art performance on various tasks.
Paper proposes a method to reuse models without raw data.
problem Reuse existing models without accessing raw data.
method Two-phase framework: Upload and Deployment phases.
result Theoretical and experimental validation of approach effectiveness.
Most companies utilize demographic information to develop their strategy in a market. However, such information is not available to most retail companies. Several studies have been conducted to predict the demographic attributes of users from their transaction histories, but they have some limitations. First, they focu…
We introduce Compositional Imitation Learning and Execution (CompILE): a framework for learning reusable, variable-length segments of hierarchically-structured behavior from demonstration data. CompILE uses a novel unsupervised, fully-differentiable sequence segmentation module to learn latent encodings of sequential d…
Enhances demonstrations with safety specifications using LTL.
problem Learning from demonstrations without safety specifications.
method Converts LTL specifications into a differentiable loss for training.
result System learns dynamic movement primitives that satisfy complex specifications.
We propose a general approach to modeling semi-supervised learning (SSL) algorithms. Specifically, we present a declarative language for modeling both traditional supervised classification tasks and many SSL heuristics, including both well-known heuristics such as co-training and novel domain-specific heuristics. In ad…
New meta-learning method handles nonlinear tasks for faster convergence.
problem Meta-learning with nonlinear representations and tasks.
method Derive theoretical guarantees with regularization in RKHS.
result Improved rates scaling with the number of tasks.