Maximizing a deep submodular function optimization with a weighted MAX-SAT problem for trajectory clustering and motion segmentation

Chandriah, Kiran Kumar; Naraganahalli, Raghavendra V.

doi:10.1007/s10489-021-02276-8

Cited by 3 publications

(1 citation statement)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…After its earlier success in many fields, deep neural networks have found a pervasive suite of applications in healthcare research including medical imaging, becoming a new de facto standard [63,24,18,58,22,72,10,67,30]. Training these networks requires a vast amount of data to achieve robust performance [12,16,56].…”

Section: Introductionmentioning

confidence: 99%

Federated Split Vision Transformer for COVID-19 CXR Diagnosis using Task-Agnostic Training

Park¹,

Kim²,

Kim³

et al. 2021

Preprint

View full text Add to dashboard Cite

Federated learning, which shares the weights of the neural network across clients, is gaining attention in the healthcare sector as it enables training on a large corpus of decentralized data while maintaining data privacy. For example, this enables neural network training for COVID-19 diagnosis on chest X-ray (CXR) images without collecting patient CXR data across multiple hospitals. Unfortunately, the exchange of the weights quickly consumes the network bandwidth if highly expressive network architecture is employed. So-called split learning partially solves this problem by dividing a neural network into a client and a server part, so that the client part of the network takes up less extensive computation resources and bandwidth. However, it is not clear how to find the optimal split without sacrificing the overall network performance. To amalgamate these methods and thereby maximize their distinct strengths, here we show that the Vision Transformer, a recently developed deep learning architecture with straightforward decomposable configuration, is ideally suitable for split learning without sacrificing performance. Even under the non-independent and identically distributed data distribution which emulates a real collaboration between hospitals using CXR datasets from multiple sources, the proposed framework was able to attain performance comparable to data-centralized training. In addition, the proposed framework along with heterogeneous multi-task clients also improves individual task performances including the diagnosis of COVID-19, eliminating the need for sharing large weights with innumerable parameters. Our results affirm the suitability of Transformer for collaborative learning in medical imaging and pave the way forward for future real-world implementations.

show abstract

Section: Introductionmentioning

confidence: 99%

Federated Split Vision Transformer for COVID-19 CXR Diagnosis using Task-Agnostic Training

Park¹,

Kim²,

Kim³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

Optimization algorithm of an artificial neural network-based controller and simulation method for animated virtual idol characters

Shi

Wang

2022

Neural Comput & Applic

View full text Add to dashboard Cite

Learning from survey propagation: a neural network for MAX-E-3-SAT

Marino

2021

Mach. Learn.: Sci. Technol.

View full text Add to dashboard Cite

Many natural optimization problems are NP-hard, which implies that they are probably hard to solve exactly in the worst-case. However, it suffices to get reasonably good solutions for all (or even most) instances in practice. This paper presents a new algorithm for computing approximate solutions in Θ(N) for the maximum exact 3-satisfiability (MAX-E-3-SAT) problem by using supervised learning methodology. This methodology allows us to create a learning algorithm able to fix Boolean variables by using local information obtained by the Survey Propagation algorithm. By performing an accurate analysis, on random conjunctive normal form instances of the MAX-E-3-SAT with several Boolean variables, we show that this new algorithm, avoiding any decimation strategy, can build assignments better than a random one, even if the convergence of the messages is not found. Although this algorithm is not competitive with state-of-the-art maximum satisfiability solvers, it can solve substantially larger and more complicated problems than it ever saw during training.

show abstract

Maximizing a deep submodular function optimization with a weighted MAX-SAT problem for trajectory clustering and motion segmentation

Cited by 3 publications

References 48 publications

Federated Split Vision Transformer for COVID-19 CXR Diagnosis using Task-Agnostic Training

Federated Split Vision Transformer for COVID-19 CXR Diagnosis using Task-Agnostic Training

Optimization algorithm of an artificial neural network-based controller and simulation method for animated virtual idol characters

Learning from survey propagation: a neural network for MAX-E-3-SAT

Contact Info

Product

Resources

About