Predicting is not understanding: Recognizing and addressing underspecification in machine learning
Abstract Machine learning (ML) models are typically optimized for their accuracy on a given
dataset. However, this predictive criterion rarely captures all desirable properties of a model …
dataset. However, this predictive criterion rarely captures all desirable properties of a model …
Childhood leukemia classification via information bottleneck enhanced hierarchical multi-instance learning
Leukemia classification relies on a detailed cytomorphological examination of Bone Marrow
(BM) smear. However, applying existing deep-learning methods to it is facing two significant …
(BM) smear. However, applying existing deep-learning methods to it is facing two significant …
Improving adversarial robustness by learning shared information
X Yu, N Smedemark-Margulies, S Aeron… - Pattern Recognition, 2023 - Elsevier
We consider the problem of improving the adversarial robustness of neural networks while
retaining natural accuracy. Motivated by the multi-view information bottleneck formalism, we …
retaining natural accuracy. Motivated by the multi-view information bottleneck formalism, we …
Progressive transfer learning for advancing machine learning-based reduced-order modeling
To maximize knowledge transfer and improve the data requirement for data-driven machine
learning (ML) modeling, a progressive transfer learning for reduced-order modeling (p …
learning (ML) modeling, a progressive transfer learning for reduced-order modeling (p …
Dynamic bottleneck with a predictable prior for image-based deep reinforcement learning
Methods based on the information bottleneck that learn compressive representations from
high-dimensional images have been proven to significantly improve the data efficiency of …
high-dimensional images have been proven to significantly improve the data efficiency of …
Partial Information Decomposition for Causal Discovery With Application to Internet of Things
JE Liang - IEEE Internet of Things Journal, 2024 - ieeexplore.ieee.org
Causal discovery is fundamental to science because the concept can be used for
predictions of the consequences of actions. Information theory for causal discovery has …
predictions of the consequences of actions. Information theory for causal discovery has …
Blockchain-based Efficient and Trustworthy AIGC Services in Metaverse
AI-Generated Content (AIGC) services are essential in developing the Metaverse, providing
various digital content to build shared virtual environments. The services can also offer …
various digital content to build shared virtual environments. The services can also offer …
Counterfactual Supervision-Based Information Bottleneck for Out-of-Distribution Generalization
Learning invariant (causal) features for out-of-distribution (OOD) generalization have
attracted extensive attention recently, and among the proposals, invariant risk minimization …
attracted extensive attention recently, and among the proposals, invariant risk minimization …
Bottleneck identification and transfer prediction for automated production lines based on FNN
H Si, H Zhou, J Guo, J Wang, Y Zhang… - Journal of Physics …, 2024 - iopscience.iop.org
In a re-entrant production system, the throughput of the whole system depends on the
capacity of the bottleneck machine. In this study, a new definition of bottleneck is proposed …
capacity of the bottleneck machine. In this study, a new definition of bottleneck is proposed …
Progressive reduced order modeling: empowering data-driven modeling with selective knowledge transfer
Data-driven modeling can suffer from a constant demand for data, leading to reduced
accuracy and impractical for engineering applications due to the high cost and scarcity of …
accuracy and impractical for engineering applications due to the high cost and scarcity of …