Novel meta-RL strategy improves efficiency in learning novel tasks.
problem Efficiency in learning novel tasks using deep RL.
method Decomposes meta-RL into task-exploration, task-inference, and task-fulfillment; uses deep networks and a task encoder.
result Improves sample efficiency and mitigates meta-overfitting.
Framework adapts to new tasks based on prior knowledge.
problem Models struggle to adapt to novel tasks without direct experience.
method Learned task representations and meta-mappings to transform them.
result Meta-mapping achieves 80-90% performance on novel tasks.
The paper reduces sample complexity for estimating novel task parameters with few meta-learning tasks.
problem Meta-learning sparse linear regression with limited data.
method Accessing multiple similar tasks to recover common support and reduce novel task sample complexity.
result The sample complexity for estimating the parameter of a novel task is greatly reduced to O(1) with respect to the number of tasks.
Despite significant progress, deep reinforcement learning (RL) suffers from data-inefficiency and limited generalization. Recent efforts apply meta-learning to learn a meta-learner from a set of RL tasks such that a novel but related task could be solved quickly. Though specific in some ways, different tasks in meta-RL…
Learning policies that generalize across multiple tasks is an important and challenging research topic in reinforcement learning and robotics. Training individual policies for every single potential task is often impractical, especially for continuous task variations, requiring more principled approaches to share and t…
In meta-learning an agent extracts knowledge from observed tasks, aiming to facilitate learning of novel future tasks. Under the assumption that future tasks are 'related' to previous tasks, the accumulated knowledge should be learned in a way which captures the common structure across learned tasks, while allowing the…
Meta-learning improves by adding more data to tasks.
problem Overfitting to meta-training tasks impairs generalization to novel tasks.
method Task augmentation methods (MetaMix and Channel Shuffle) are proposed to improve generalization.
result MetaMix and Channel Shuffle outperform state-of-the-art results across multiple datasets.
Novel methods generate diverse policies in reinforcement learning.
problem Generating diverse policies in reinforcement learning.
method Constrained optimization perspective, introducing new metrics, and novel policy generation methods.
result Improved novelty and performance of generated policies.
New algorithms minimize regret in multi-task and lifelong linear bandits with shared representation.
problem Minimizing regret in multi-task and lifelong linear bandits with shared representation.
method Novel algorithms using efficient estimator for low-rank linear feature extractor and novel analysis.
result Achieved regret bounds matching minimax lower bound up to logarithmic factors.
This study tackles mutual fund portfolio prediction, focusing on novel items.
problem Predicting novel items in mutual fund portfolios is challenging and less explored.
method Created a comprehensive benchmark dataset and evaluated various recommender system models.
result Autoencoder-based approaches outperform state-of-the-art models in predicting novel items.
AuxiLearn combines auxiliary tasks into a single loss function.
problem Improving neural network performance on a main task using auxiliary tasks.
method Implicit differentiation to learn a network that combines auxiliary tasks into a single coherent objective function.
result AuxiLearn consistently outperforms competing methods in various tasks and domains.
Novel GNN for signed and directed networks using magnetic signed Laplacian.
problem Efficiently modeling signed and directed networks for tasks like clustering and link prediction.
method Introduced a magnetic signed Laplacian for directed signed graphs, used it to construct a spectral GNN.
result Demonstrated effective performance on tasks involving signed and directional information.
In this work, we present a reinforcement learning algorithm that can find a variety of policies (novel policies) for a task that is given by a task reward function. Our method does this by creating a second reward function that recognizes previously seen state sequences and rewards those by novelty, which is measured u…
A major challenge in reinforcement learning is exploration, when local dithering methods such as epsilon-greedy sampling are insufficient to solve a given task. Many recent methods have proposed to intrinsically motivate an agent to seek novel states, driving the agent to discover improved reward. However, while state-…
Few-shot learning is the process of learning novel classes using only a few examples and it remains a challenging task in machine learning. Many sophisticated few-shot learning algorithms have been proposed based on the notion that networks can easily overfit to novel examples if they are simply fine-tuned using only a…
We propose a framework that learns a representation transferable across different domains and tasks in a label efficient manner. Our approach battles domain shift with a domain adversarial loss, and generalizes the embedding to novel task using a metric learning-based approach. Our model is simultaneously optimized on …
Multi-task learning is a powerful method for solving multiple correlated tasks simultaneously. However, it is often impossible to find one single solution to optimize all the tasks, since different tasks might conflict with each other. Recently, a novel method is proposed to find one single Pareto optimal solution with…
Paper tackles robust knowledge transfer in parallel RL tasks.
problem Transfer knowledge from low-tier to high-tier tasks in parallel RL without shared dynamics or reward functions.
method Identifies Optimal Value Dominance condition and proposes online learning algorithms for both tasks.
result Achieves constant regret on partial states and near-optimal regret when tasks are dissimilar.
RTE enables extrapolation to new tasks by learning task transformations.
problem Learning systems struggle to generalize to unseen tasks.
method Relational Task Extrapolator (RTE) learns task transformations to enable extrapolation.
result RTE substantially outperforms existing approaches on extrapolation tasks.
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.
Agents struggle with solving tasks in new environments, but new models improve performance.
problem Rapid task-solving in novel environments.
method Developed EPNs to enable deep RL agents to plan over gathered knowledge.
result EPNs enable deep RL agents to excel at RTS, outperforming baselines by factors of 2-3.
Adversarial weighting improves regression task adaptation.
problem Improving regression performance across domains with covariate shift.
method Adversarial network algorithm for instance weighting and task learning.
result The method enhances regression accuracy on target domains.
Develops neural network for directed hypergraphs for node classification.
problem Irregular data structure, particularly directed graphs.
method Directed hypergraph neural network and semi-supervised learning method.
result Novel directed hypergraph neural network achieves highest accuracies on node classification tasks.
Cellular Electron Cryo-Tomography (CECT) is a powerful 3D imaging tool for studying the native structure and organization of macromolecules inside single cells. For systematic recognition and recovery of macromolecular structures captured by CECT, methods for several important tasks such as subtomogram classification a…
Auxiliary Tuning adapts pre-trained models for novel tasks efficiently.
problem Adapting pre-trained models for new tasks efficiently.
method Supplementing pre-trained model with an auxiliary model that shifts output distribution.
result Achieved similar results to training from scratch with fewer resources.
Causal reasoning has been an indispensable capability for humans and other intelligent animals to interact with the physical world. In this work, we propose to endow an artificial agent with the capability of causal reasoning for completing goal-directed tasks. We develop learning-based approaches to inducing causal kn…
DUET optimizes LLM training data mixtures using feedback from unseen tasks.
problem Optimizing LLM performance on unseen tasks without prior data knowledge.
method Interleaves influence function with Bayesian optimization for data selection.
result DUET converges to optimal training data mixture for unseen tasks.
BeST metric selects best source models for transfer learning.
problem Efficiently selecting top source models for a new target task.
method Quantization-level optimization procedure for similarity measure.
result BeST consistently identifies best source models for target tasks.
Deep learning (DL) advances state-of-the-art reinforcement learning (RL), by incorporating deep neural networks in learning representations from the input to RL. However, the conventional deep neural network architecture is limited in learning representations for multi-task RL (MT-RL), as multiple tasks can refer to di…
Novel representer theorem for metric and preference learning in RKHSs.
problem Metric and preference learning problems in Hilbert spaces.
method Regularization with respect to task structure norm, RKHS representation, and novel algorithm.
result Significant performance improvement over baseline methods in real-world rank inference benchmarks.
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.
Paper proposes a novel MTL framework for personalized modeling of diverse individuals.
problem Personalized modeling of heterogeneous subpopulations with high-dimensional data.
method Low-rank tensor decomposition for multi-task learning.
result Superior performance compared to benchmarks in diverse subpopulation scenarios.
SXL embeds spatial autocorrelation into neural networks for better geographic data learning.
problem Difficulties in learning spatial effects for neural networks in geographic data.
method SXL uses auxiliary tasks and autoregressive embeddings to learn spatial autocorrelation.
result SXL improves neural network training in unsupervised and supervised learning tasks.
The paper proposes new strategies to exploit relationships between meta-tasks for better few-shot learning.
problem Few-shot learning struggles with domain gaps and poorly sampled data.
method Proposes exploiting relationships between meta-tasks to improve robustness and performance.
result Developed new learning objectives (MDA and MKD) to address domain gaps and improve robustness.
Deep neural networks excel in regimes with large amounts of data, but tend to struggle when data is scarce or when they need to adapt quickly to changes in the task. In response, recent work in meta-learning proposes training a meta-learner on a distribution of similar tasks, in the hopes of generalization to novel but…
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.
New method for MTL with varying sparsity patterns across tasks.
problem Jointly training multiple linear models with differing sparsity patterns.
method Mixed-integer programming formulation and scalable algorithms.
result Our methods leverage shared support information to improve variable selection.
Meta-learning for few-shot learning allows a machine to leverage previously acquired knowledge as a prior, thus improving the performance on novel tasks with only small amounts of data. However, most mainstream models suffer from catastrophic forgetting and insufficient robustness issues, thereby failing to fully retai…
Learning suitable and well-performing dialogue behaviour in statistical spoken dialogue systems has been in the focus of research for many years. While most work which is based on reinforcement learning employs an objective measure like task success for modelling the reward signal, we use a reward based on user satisfa…
A novel gradient-based method optimizes decision trees for complex tasks.
problem Training decision trees with arbitrary differentiable loss functions.
method Gradient-based optimization using first and second derivatives of loss functions.
result Improves accuracy and flexibility in decision tree optimization.
Paper presents novel online MTL methods using WRLS and OSLSSVR.
problem Online Multi-Task Learning (MTL) Regression Problems
method Develops recursive versions of WRLS and OSLSSVR for MTL.
result Achieves exact and approximate recursions with quadratic cost.
A novel framework quantifies uncertainty using proper scores for various tasks.
problem Uncertainty quantification in machine learning for reliable applications.
method Proposes a general framework based on proper scores for epistemic, aleatoric uncertainty, and model calibration.
result Achieves state-of-the-art uncertainty estimation for large language models and generative models.
MT-HAL learns features and task associations for multiple tasks with a shared sparse structure.
problem Learning features and task associations for multiple tasks with shared structure.
method Fully nonparametric approach that learns features, samples, and task associations with a shared sparse structure.
result MT-HAL achieves a powerful convergence rate and outperforms other methods across various simulation settings.
Improves contrastive learning invariance with novel training objectives and feature averaging.
problem Contrastive learning's implicit invariance is insufficient for robust performance.
method Introduces a novel training objective and feature averaging approach to enforce invariance.
result Improved performance and robustness to transformations on downstream tasks.
Paper estimates noise covariance in correlated multi-task linear models.
problem Estimating noise covariance in multi-task high-dimensional linear models with correlated noise.
method Uses multi-task elastic-net and lasso estimators to estimate noise covariance, correcting bias in squared residual matrix.
result Develops a novel estimator of noise covariance that converges at rate n−1/2, matching oracle estimator under suitable conditions. Novel framework for Bayesian neural networks incorporating task-specific constraints.
problem Task-specific constraints in supervised model deployment.
method Introduces Output-Constrained BNN (OC-BNN) framework.
result OC-BNNs effectively incorporate prior expert knowledge and desiderata like safety and fairness.
Novel financial time-series data representation improves industry sector classification.
problem Classifying industries using historical stock returns time-series data.
method Proposed a novel representation based on stock returns embeddings for time-series data, overcoming representational challenges of conventional approaches.
result Substantial performance improvements over baselines using conventional representations.
How can we build agents that keep learning from experience, quickly and efficiently, after their initial training? Here we take inspiration from the main mechanism of learning in biological brains: synaptic plasticity, carefully tuned by evolution to produce efficient lifelong learning. We show that plasticity, just li…