Interactive concept bottleneck models

K Chauhan, R Tiwari, J Freyberg, P Shenoy… - Proceedings of the …, 2023 - ojs.aaai.org
Abstract Concept bottleneck models (CBMs) are interpretable neural networks that first
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 …

Learning to maximize mutual information for dynamic feature selection

IC Covert, W Qiu, M Lu, NY Kim… - International …, 2023 - proceedings.mlr.press
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 …

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 …

A unified active learning framework for annotating graph data with application to software source code performance prediction

P Samoaa, L Aronsson, A Longa, P Leitner… - arXiv preprint arXiv …, 2023 - arxiv.org
Most machine learning and data analytics applications, including performance engineering
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

P Samoaa, L Aronsson, A Longa, P Leitner… - … Applications of Artificial …, 2024 - Elsevier
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 …

Learning to retrieve videos by asking questions

A Madasu, J Oliva, G Bertasius - Proceedings of the 30th ACM …, 2022 - dl.acm.org
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 …

Partially observable cost-aware active-learning with large language models

N Astorga, T Liu, N Seedat… - The Thirty-Eighth Annual …, 2024 - openreview.net
Conducting experiments and gathering data for machine learning models is a complex and
expensive endeavor, particularly when confronted with limited information. Typically …

Deep reinforcement learning for cost-effective medical diagnosis

Z Yu, Y Li, J Kim, K Huang, Y Luo, M Wang - arXiv preprint arXiv …, 2023 - arxiv.org
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 …

Difa: Differentiable feature acquisition

A Ghosh, A Lan - Proceedings of the AAAI Conference on Artificial …, 2023 - ojs.aaai.org
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 …