Graceful Degradation and Related Fields

Dymond, Jack

doi:10.48550/arxiv.2106.11119

Cited by 2 publications

(2 citation statements)

References 69 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is partly due to the fact that there are two types of uncertainty—aleatory and epistemic uncertainty. In this case, the aleatory uncertainty cannot be eliminated, because it is an inherent part of the observed process or object ( 46 ). On the other hand, there are many calibration algorithms, each of which depends on a large number of hyperparameters.…”

Section: Discussionmentioning

confidence: 99%

Resilience-aware MLOps for AI-based medical diagnostic system

Moskalenko,

Kharchenko

2024

Front. Public Health

View full text Add to dashboard Cite

BackgroundThe healthcare sector demands a higher degree of responsibility, trustworthiness, and accountability when implementing Artificial Intelligence (AI) systems. Machine learning operations (MLOps) for AI-based medical diagnostic systems are primarily focused on aspects such as data quality and confidentiality, bias reduction, model deployment, performance monitoring, and continuous improvement. However, so far, MLOps techniques do not take into account the need to provide resilience to disturbances such as adversarial attacks, including fault injections, and drift, including out-of-distribution. This article is concerned with the MLOps methodology that incorporates the steps necessary to increase the resilience of an AI-based medical diagnostic system against various kinds of disruptive influences.MethodsPost-hoc resilience optimization, post-hoc predictive uncertainty calibration, uncertainty monitoring, and graceful degradation are incorporated as additional stages in MLOps. To optimize the resilience of the AI based medical diagnostic system, additional components in the form of adapters and meta-adapters are utilized. These components are fine-tuned during meta-training based on the results of adaptation to synthetic disturbances. Furthermore, an additional model is introduced for post-hoc calibration of predictive uncertainty. This model is trained using both in-distribution and out-of-distribution data to refine predictive confidence during the inference mode.ResultsThe structure of resilience-aware MLOps for medical diagnostic systems has been proposed. Experimentally confirmed increase of robustness and speed of adaptation for medical image recognition system during several intervals of the system’s life cycle due to the use of resilience optimization and uncertainty calibration stages. The experiments were performed on the DermaMNIST dataset, BloodMNIST and PathMNIST. ResNet-18 as a representative of convolutional networks and MedViT-T as a representative of visual transformers are considered. It is worth noting that transformers exhibited lower resilience than convolutional networks, although this observation may be attributed to potential imperfections in the architecture of adapters and meta-adapters.СonclusionThe main novelty of the suggested resilience-aware MLOps methodology and structure lie in the separating possibilities and activities on creating a basic model for normal operating conditions and ensuring its resilience and trustworthiness. This is significant for the medical applications as the developer of the basic model should devote more time to comprehending medical field and the diagnostic task at hand, rather than specializing in system resilience. Resilience optimization increases robustness to disturbances and speed of adaptation. Calibrated confidences ensure the recognition of a portion of unabsorbed disturbances to mitigate their impact, thereby enhancing trustworthiness.

show abstract

Section: Discussionmentioning

confidence: 99%

Resilience-aware MLOps for AI-based medical diagnostic system

Moskalenko,

Kharchenko

2024

Front. Public Health

View full text Add to dashboard Cite

show abstract

“…Producing models which give confidence aware output distributions is one method of identifying both adversarial and OOD inputs, and these models have been studied in great detail [12,33,3]. Some methods incorporate additional data into their methodology [11,44], some use data augmentation/generation [30,25,20,36,41,45], while others use probabilistic models to adapt their loss functions [37,28,6,47].…”

Section: Related Workmentioning

confidence: 99%

Exploiting Epistemic Uncertainty at Inference Time for Early-Exit Power Saving

Dymond,

Stein,

Gunn

2023

Frontiers in Artificial Intelligence and Applications

View full text Add to dashboard Cite

Distinguishing epistemic from aleatoric uncertainty is a central idea to out-of-distribution (OOD) detection. By interpreting adversarial and OOD inputs from this perspective, we can collect them into a single unclassifiable group. Rejecting such inputs mid-inference will reduce resource usage. To achieve this, we apply k-nearest neighbour (KNN) classifiers to the embedding space of branched neural networks. This introduces a novel means of additional power savings, through an early-exit reject. Our technique works out-of-the-box on any branched neural network and can be competitive on OOD benchmarks, achieving an area under receiver operator characteristic (AUROC) of over 0.9 in most datasets, and scores of 0.95+ when identifying perturbed inputs. A mixed input test set is introduced, we show how OOD inputs can be identified up to 50% of the time, and adversarial inputs up to 85% of the time. In a balanced test environment, this equates to power savings of up to 18% in the OOD scenario and 40% in the adversarial scenario. This allows a more stringent in-distribution (ID) classification policy, leading to accuracy improvements of 15% and 20% on the OOD and adversarial tests, respectively, when compared to conventional exit policies operating under the same conditions.

show abstract

Graceful Degradation and Related Fields

Cited by 2 publications

References 69 publications

Resilience-aware MLOps for AI-based medical diagnostic system

Resilience-aware MLOps for AI-based medical diagnostic system

Exploiting Epistemic Uncertainty at Inference Time for Early-Exit Power Saving

Contact Info

Product

Resources

About