arXiv research

Unified MTL framework for heterogeneous data integrates shared and task-specific encoders.

Improves shared encoder representations for better multi-task learning performance.

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…

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…

GraphToken encodes structured data for LLMs, improving graph reasoning tasks.

Configuration spaces for computer systems can be challenging for traditional and automatic tuning strategies. Injecting task-specific knowledge into the tuner for a task may allow for more efficient exploration of candidate configurations. We apply this idea to the task of index set selection to accelerate database wor…

New technique reduces bias in DNN models without sensitive attribute annotations.

Unified scoring model improves efficiency and performance across multiple tasks.

Pre-trained word embeddings encode general word semantics and lexical regularities of natural language, and have proven useful across many NLP tasks, including word sense disambiguation, machine translation, and sentiment analysis, to name a few. In supervised tasks such as multiclass text classification (the focus of …

Stein-Encoder isolates genetic signals in multi-modal biomedical data.

Method learns equivariances from data without custom architecture design.

Medical imaging models may encode demographic attributes without violating fairness, depending on the approach.

This paper describes a language representation model which combines the Bidirectional Encoder Representations from Transformers (BERT) learning mechanism described in Devlin et al. (2018) with a generalization of the Universal Transformer model described in Dehghani et al. (2018). We further improve this model by addin…

The paper analyzes how guidance affects diffusion models using Gaussian mixture models.

Low-rank framework for task-specific LLM ranking from sparse comparisons.

Meta-learning improves Gaussian process uncertainty estimation.

Clinical notes are a rich source of information about patient state. However, using them to predict clinical events with machine learning models is challenging. They are very high dimensional, sparse and have complex structure. Furthermore, training data is often scarce because it is expensive to obtain reliable labels…

Many real-world problems, including multi-speaker text-to-speech synthesis, can greatly benefit from the ability to meta-learn large models with only a few task-specific components. Updating only these task-specific modules then allows the model to be adapted to low-data tasks for as many steps as necessary without ris…

FedGTEA learns new tasks in federated learning with task embeddings and alignment.

BTZSC benchmarks zero-shot text classification across diverse models.

New method prevents forgetting in LLMs by dynamically identifying task-specific subspaces.

Algorithm learns which weights to share in deep multi-task learning.

Transformers can emulate various algorithms by prompting, proving universality.

CCM improves context for Meta-RL by contrastive learning.

In many settings (e.g., robotics) demonstrations provide a natural way to specify tasks; however, most methods for learning from demonstrations either do not provide guarantees that the artifacts learned for the tasks, such as rewards or policies, can be safely composed and/or do not explicitly capture history dependen…

Two simple methods learn fair metrics from data to improve fairness in ML tasks.

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…

New method uses bi-level optimization to learn useful representations for imitation learning.

Recent advancements in language representation models such as BERT have led to a rapid improvement in numerous natural language processing tasks. However, language models usually consist of a few hundred million trainable parameters with embedding space distributed across multiple layers, thus making them challenging t…

A framework evaluates the impact of different modules in graph contrastive learning.

A tensor model for meta-learning adapts to task-specific features.

UCB-TQL learns from multiple tasks with shared dynamics and adapts to task-specific variations.

Hybrid framework prevents forgetting in continual learning.

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…

This research improves multitask learning by creating task-specific pathways.

Swarm systems constitute a challenging problem for reinforcement learning (RL) as the algorithm needs to learn decentralized control policies that can cope with limited local sensing and communication abilities of the agents. While it is often difficult to directly define the behavior of the agents, simple communicatio…

STAR improves equivariant and invariant representation learning by routing projection heads.

Study evaluates how much knowledge LLMs have by comparing their prediction accuracy to flexible models.

Enhances GNNs to better capture local graph structures.

AFTER technique improves NLP models by preventing overfitting to task-specific domains.

SPARC improves continual learning with minimal memory and computational overhead.

Graph representation learning, aiming to learn low-dimensional representations which capture the geometric dependencies between nodes in the original graph, has gained increasing popularity in a variety of graph analysis tasks, including node classification and link prediction. Existing representation learning methods …

Meta-learning shows negative transfer between tasks, which MetaCRL addresses.

In this work, we connect two distinct concepts for unsupervised domain adaptation: feature distribution alignment between domains by utilizing the task-specific decision boundary and the Wasserstein metric. Our proposed sliced Wasserstein discrepancy (SWD) is designed to capture the natural notion of dissimilarity betw…

Bayesian framework optimizes 3D view selection for specific tasks.

We present a class of algorithms capable of directly training deep neural networks with respect to large families of task-specific performance measures such as the F-measure and the Kullback-Leibler divergence that are structured and non-decomposable. This presents a departure from standard deep learning techniques tha…

Algorithm identifies and transfers unstable features to create robust classifiers.

POLAR learns efficient data acquisition policies using pretrained belief representations.