Interactive concept bottleneck models
Abstract Concept bottleneck models (CBMs) are interpretable neural networks that first
predict labels for human-interpretable concepts relevant to the prediction task, and then …
predict labels for human-interpretable concepts relevant to the prediction task, and then …
Learning to receive help: Intervention-aware concept embedding models
M Espinosa Zarlenga, K Collins… - Advances in …, 2024 - proceedings.neurips.cc
Abstract Concept Bottleneck Models (CBMs) tackle the opacity of neural architectures by
constructing and explaining their predictions using a set of high-level concepts. A special …
constructing and explaining their predictions using a set of high-level concepts. A special …
Learning to maximize mutual information for dynamic feature selection
Feature selection helps reduce data acquisition costs in ML, but the standard approach is to
train models with static feature subsets. Here, we consider the dynamic feature selection …
train models with static feature subsets. Here, we consider the dynamic feature selection …
Building Expressive and Tractable Probabilistic Generative Models: A Review
S Sidheekh, S Natarajan - arXiv preprint arXiv:2402.00759, 2024 - arxiv.org
We present a comprehensive survey of the advancements and techniques in the field of
tractable probabilistic generative modeling, primarily focusing on Probabilistic Circuits …
tractable probabilistic generative modeling, primarily focusing on Probabilistic Circuits …
A unified active learning framework for annotating graph data with application to software source code performance prediction
Most machine learning and data analytics applications, including performance engineering
in software systems, require a large number of annotations and labelled data, which might …
in software systems, require a large number of annotations and labelled data, which might …
[HTML][HTML] A unified active learning framework for annotating graph data for regression task
In many domains, effectively applying machine learning models requires a large number of
annotations and labelled data, which might not be available in advance. Acquiring …
annotations and labelled data, which might not be available in advance. Acquiring …
Learning to retrieve videos by asking questions
The majority of traditional text-to-video retrieval systems operate in static environments, ie,
there is no interaction between the user and the agent beyond the initial textual query …
there is no interaction between the user and the agent beyond the initial textual query …
Partially observable cost-aware active-learning with large language models
Conducting experiments and gathering data for machine learning models is a complex and
expensive endeavor, particularly when confronted with limited information. Typically …
expensive endeavor, particularly when confronted with limited information. Typically …
Deep reinforcement learning for cost-effective medical diagnosis
Dynamic diagnosis is desirable when medical tests are costly or time-consuming. In this
work, we use reinforcement learning (RL) to find a dynamic policy that selects lab test panels …
work, we use reinforcement learning (RL) to find a dynamic policy that selects lab test panels …
Difa: Differentiable feature acquisition
Feature acquisition in predictive modeling is an important task in many practical
applications. For example, in patient health prediction, we do not fully observe their personal …
applications. For example, in patient health prediction, we do not fully observe their personal …