A glass-box interactive machine learning approach for solving NP-hard problems with the human-in-the-loop

By Andreas Holzinger, Markus Plass, Katharina Holzinger, Gloria Cerasela Crisan, Camelia-M. Pintea, Vasile Palade. 2017

98 citations recorded by the source corpus.

The ultimate goal of the Machine Learning (ML) community is to develop algorithms that can automatically learn from data, to extract knowledge and to make decisions without any human intervention. Specifically, automatic Machine Learning (aML) approaches show impressive success, e.g. in speech/image recognition or autonomous drive and smart car industry. Recent results even demonstrate intriguingly that deep learning applied for automatic classification of skin lesions is on par with the performance of dermatologists, yet outperforms the average human efficiency. As human perception is inherently limited to 3D environments, such approaches can discover patterns, e.g. that two objects are similar, in arbitrarily high-dimensional spaces what no human is able to do. Humans can deal simultaneously only with limited amounts of data, whilst “big data” is not only beneficial but necessary for aML. However, in health informatics, there are few data sets; aML approaches often suffer from insufficient training samples. Many problems are computationally hard, e.g. subspace clustering, k-anonymization, or protein folding. Here, interactive machine learning (iML) could be successfully used, as a human-in-the-loop contributes to reduce a huge search space through heuristic selection of suitable samples. This can reduce the complexity of NP-hard problems through the knowledge brought in by a human agent involved into the learning algorithm. A huge motivation for iML is that standard black-box approaches lack transparency, hence do not foster trust and acceptance of ML among end-users. Most of all, rising legal and privacy aspects, e.g. the European General Data Protection Regulations (GDPR) make black-box approaches difficult to use, because they often are not able to explain why a decision has been made, e.g. why two objects are similar. All these reasons motivate the idea to open the black-box to a glass-box. In this paper, we present some experiments to demonstrate the effectiveness of the iML human-in-the-loop model, in particular when using a glass-box instead of a black-box model and thus enabling a human directly to interact with a learning algorithm. We selected the Ant Colony System (ACS) algorithm, and applied it on the Traveling Salesman Problem (TSP). The TSP-problem is a good example, because it is of high relevance for health informatics as for example on protein folding problem, thus of enormous importance for fostering cancer research. Finally, from studies of learning from observation, i.e. of how humans extract so much from so little data, fundamental ML-research also may benefit.

Subfields: Artificial Intelligence, Automotive Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Automotive Engineering

Citations in the corpus

Explainable AI: The New 42? (2018, background): “So emerges the urgent need to make results and machine decisions transparent, understandable and explainable [9–11].”
Explanation Methods in Deep Learning: Users, Values, Concerns and Challenges (2018, background): “Because of these complications DNNs are often called black box models, as opposed to glassbox models [25].”
What do we need to build explainable AI systems for the medical domain? (2017, methodology): “Ante-hoc systems are interpretable by design towards glass-box approaches (Holzinger et al., 2017c); typical examples include linear regression, decision trees and fuzzy inference systems.”
A Survey on the Explainability of Supervised Machine Learning (2020, background): “Holzinger et al. (2017) summarized the aim of this by concluding to make use of the human cognitive abilities when machines fail.”
Causability and explainability of artificial intelligence in medicine (2019, methodology): “Ante-hoc systems are interpretable by design towards glass-box approaches (Holzinger et al., 2017, 2018); typical examples include linear regression, decision trees and fuzzy inference systems.”
Legal, regulatory, and ethical frameworks for development of standards in artificial intelligence (AI) and autonomous robotic surgery (2019, background): “32 A much more compelling argument for iML is that current approaches lack explicit declarative knowledge, therefore lacking trans-parency.”
Towards Integrative Machine Learning and Knowledge Extraction (2017, methodology): “For instance, the Census Bureau’s Person Identification Validation System is a production system that uses PRL [11,12] for matching person records arising from censuses records, survey datasets, administrative records, or commercial files.”
Entity-Centric Information Access with Human in the Loop for the Biomedical Domain (2017, background): “Key to the approach is to think the user in the center of the process and offer the user an adaptive ML environment (Holzinger, 2016; Holzinger et al., 2017) where manual effort in terms of annotating entities or classifying relations immediately pays of in an improved representation in the EG.”