arXiv research

New algorithm improves learning efficiency in multi-task contextual bandits.

This paper explores the complexity of learning representations in contextual linear bandits.

Taxonomies are semantic hierarchies of concepts. One limitation of current taxonomy learning systems is that they define concepts as single words. This position paper argues that contextualized word representations, which recently achieved state-of-the-art results on many competitive NLP tasks, are a promising method t…

Social bias in machine learning has drawn significant attention, with work ranging from demonstrations of bias in a multitude of applications, curating definitions of fairness for different contexts, to developing algorithms to mitigate bias. In natural language processing, gender bias has been shown to exist in contex…

Enhances GNNs with text features for better fake news detection.

SLiCE learns contextual node embeddings for link prediction in heterogeneous networks.

We consider an online decision making setting known as contextual bandit problem, and propose an approach for improving contextual bandit performance by using an adaptive feature extraction (representation learning) based on online clustering. Our approach starts with an off-line pre-training on unlabeled history of co…

Elliptical Attention improves transformer performance by focusing on contextually relevant features.

Proposes a framework to extract ordered eigenfunctions from contextual kernels.

New algorithm for context bandits with continuous actions.

Predict stock movement with news headlines using BERT embeddings.

We extend manifold capacity to nonlinear neural representations with contextual information.

Novel approach to contextual bandits using self-supervised learning.

A new algorithm learns from raw feature vectors using deep neural networks and UCB for exploration.

Meta learning improves with contextualizers that adapt to examples.

The paper proposes a deep learning technique for structured and composable representations.

Machine learning methods have recently achieved high-performance in biomedical text analysis. However, a major bottleneck in the widespread application of these methods is obtaining the required large amounts of annotated training data, which is resource intensive and time consuming. Recent progress in self-supervised …

SCNode improves node embeddings for GNNs in both homophilic and heterophilic graphs.

Neural-$σ^2$-LinearUCB improves regret in neural contextual bandits.

Method learns evolving policies in healthcare contexts.

Method learns audio embeddings with contextualized tags.

New method for online statistical inference in contextual bandits using SGD.

Study identifies methods for handling sparse data in web settings with contextual bandits.

We describe MELEE, a meta-learning algorithm for learning a good exploration policy in the interactive contextual bandit setting. Here, an algorithm must take actions based on contexts, and learn based only on a reward signal from the action taken, thereby generating an exploration/exploitation trade-off. MELEE address…

Faster, context-aware topic modeling approach unveiled.

LoCo-RLHF models diverse human feedback with contextual information.

Scarce data is a major challenge to scaling robot learning to truly complex tasks, as we need to generalize locally learned policies over different task contexts. Contextual policy search offers data-efficient learning and generalization by explicitly conditioning the policy on a parametric context space. In this paper…

Context-aware recommender systems (CARSs) apply sensing and analysis of user context in order to provide personalized services. Adding context to a recommendation model is challenging, since the addition of context may increases both the dimensionality and sparsity of the model. Recent research has shown that modeling …

REN addresses uncertainty in user feedbacks for better recommendation systems.

Paper studies linear CMDPs, improving sample complexity for both models.

We study the stochastic contextual bandit problem, where the reward is generated from an unknown function with additive noise. No assumption is made about the reward function other than boundedness. We propose a new algorithm, NeuralUCB, which leverages the representation power of deep neural networks and uses a neural…

New algorithm for fair ranking in contextual bandits with concave rewards.

Multi-head attention mechanism is capable of learning various representations from sequential data while paying attention to different subsequences, e.g., word-pieces or syllables in a spoken word. From the subsequences, it retrieves richer information than a single-head attention which only summarizes the whole sequen…

NeuralRBMLE tackles explore-exploit trade-offs in contextual bandits with neural networks.

Contextualizing financial news improves stock price predictions.

A new approach learns to represent context for nonstationary bandits.

Embedding models, which learn latent representations of users and items based on user-item interaction patterns, are a key component of recommendation systems. In many applications, contextual constraints need to be applied to refine recommendations, e.g. when a user specifies a price range or product category filter. …

Meta-learning for bandit tasks using shared representations.

Automates debiasing for large language model evaluations through Fisher random walk.

Blood glucose value prediction is an important task in diabetes management. While it is reported that glucose concentration is sensitive to social context such as mood, physical activity, stress, diet, alongside the influence of diabetes pathologies, we need more research on data and methodologies to incorporate and ev…

New approach improves cross-domain recommendation for sparse target domains.

This paper investigates how transformers can learn to generalize to unseen examples in context.

AGG-UCB uses neural networks to optimize group behaviors in contextual bandits.

Contextualized ML learns context-dependent effects using deep learning.

IDS improves reinforcement learning with contextual information.

We design and study a Contextual Memory Tree (CMT), a learning memory controller that inserts new memories into an experience store of unbounded size. It is designed to efficiently query for memories from that store, supporting logarithmic time insertion and retrieval operations. Hence CMT can be integrated into existi…

Representation learning is an essential problem in a wide range of applications and it is important for performing downstream tasks successfully. In this paper, we propose a new model that learns coupled representations of domains, intents, and slots by taking advantage of their hierarchical dependency in a Spoken Lang…

SADCBO optimizes contextual variables by balancing relevance and cost.