Receive a weekly summary and discussion of the top papers of the week by leading researchers in the field.

General General

Importance measures derived from random forests: characterisation and extension

ArXiv Preprint

Nowadays new technologies, and especially artificial intelligence, are more and more established in our society. Big data analysis and machine learning, two sub-fields of artificial intelligence, are at the core of many recent breakthroughs in many application fields (e.g., medicine, communication, finance, ...), including some that are strongly related to our day-to-day life (e.g., social networks, computers, smartphones, ...). In machine learning, significant improvements are usually achieved at the price of an increasing computational complexity and thanks to bigger datasets. Currently, cutting-edge models built by the most advanced machine learning algorithms typically became simultaneously very efficient and profitable but also extremely complex. Their complexity is to such an extent that these models are commonly seen as black-boxes providing a prediction or a decision which can not be interpreted or justified. Nevertheless, whether these models are used autonomously or as a simple decision-making support tool, they are already being used in machine learning applications where health and human life are at stake. Therefore, it appears to be an obvious necessity not to blindly believe everything coming out of those models without a detailed understanding of their predictions or decisions. Accordingly, this thesis aims at improving the interpretability of models built by a specific family of machine learning algorithms, the so-called tree-based methods. Several mechanisms have been proposed to interpret these models and we aim along this thesis to improve their understanding, study their properties, and define their limitations.

Antonio Sutera

2021-06-17

Pathology Pathology

Exploring the Properties and Evolution of Neural Network Eigenspaces during Training

ArXiv Preprint

In this work we explore the information processing inside neural networks using logistic regression probes \cite{probes} and the saturation metric \cite{featurespace_saturation}. We show that problem difficulty and neural network capacity affect the predictive performance in an antagonistic manner, opening the possibility of detecting over- and under-parameterization of neural networks for a given task. We further show that the observed effects are independent from previously reported pathological patterns like the ``tail pattern'' described in \cite{featurespace_saturation}. Finally we are able to show that saturation patterns converge early during training, allowing for a quicker cycle time during analysis

Mats L. Richter Leila Malihi Anne-Kathrin Patricia Windler Ulf Krumnack

2021-06-17

General General

Privacy-Preserving Eye-tracking Using Deep Learning

ArXiv Preprint

The expanding usage of complex machine learning methods like deep learning has led to an explosion in human activity recognition, particularly applied to health. In particular, as part of a larger body sensor network system, face and full-body analysis is becoming increasingly common for evaluating health status. However, complex models which handle private and sometimes protected data, raise concerns about the potential leak of identifiable data. In this work, we focus on the case of a deep network model trained on images of individual faces. Full-face video recordings taken from 493 individuals undergoing an eye-tracking based evaluation of neurological function were used. Outputs, gradients, intermediate layer outputs, loss, and labels were used as inputs for a deep network with an added support vector machine emission layer to recognize membership in the training data. The inference attack method and associated mathematical analysis indicate that there is a low likelihood of unintended memorization of facial features in the deep learning model. In this study, it is showed that the named model preserves the integrity of training data with reasonable confidence. The same process can be implemented in similar conditions for different models.

Salman Seyedi, Zifan Jiang, Allan Levey, Gari D. Clifford

2021-06-17

General General

Classifying vaccine sentiment tweets by modelling domain-specific representation and commonsense knowledge into context-aware attentive GRU

ArXiv Preprint

Vaccines are an important public health measure, but vaccine hesitancy and refusal can create clusters of low vaccine coverage and reduce the effectiveness of vaccination programs. Social media provides an opportunity to estimate emerging risks to vaccine acceptance by including geographical location and detailing vaccine-related concerns. Methods for classifying social media posts, such as vaccine-related tweets, use language models (LMs) trained on general domain text. However, challenges to measuring vaccine sentiment at scale arise from the absence of tonal stress and gestural cues and may not always have additional information about the user, e.g., past tweets or social connections. Another challenge in LMs is the lack of commonsense knowledge that are apparent in users metadata, i.e., emoticons, positive and negative words etc. In this study, to classify vaccine sentiment tweets with limited information, we present a novel end-to-end framework consisting of interconnected components that use domain-specific LM trained on vaccine-related tweets and models commonsense knowledge into a bidirectional gated recurrent network (CK-BiGRU) with context-aware attention. We further leverage syntactical, user metadata and sentiment information to capture the sentiment of a tweet. We experimented using two popular vaccine-related Twitter datasets and demonstrate that our proposed approach outperforms state-of-the-art models in identifying pro-vaccine, anti-vaccine and neutral tweets.

Usman Naseem, Matloob Khushi, Jinman Kim, Adam G. Dunn

2021-06-17

General General

Predicting cognitive scores with graph neural networks through sample selection learning

ArXiv Preprint

Analyzing the relation between intelligence and neural activity is of the utmost importance in understanding the working principles of the human brain in health and disease. In existing literature, functional brain connectomes have been used successfully to predict cognitive measures such as intelligence quotient (IQ) scores in both healthy and disordered cohorts using machine learning models. However, existing methods resort to flattening the brain connectome (i.e., graph) through vectorization which overlooks its topological properties. To address this limitation and inspired from the emerging graph neural networks (GNNs), we design a novel regression GNN model (namely RegGNN) for predicting IQ scores from brain connectivity. On top of that, we introduce a novel, fully modular sample selection method to select the best samples to learn from for our target prediction task. However, since such deep learning architectures are computationally expensive to train, we further propose a \emph{learning-based sample selection} method that learns how to choose the training samples with the highest expected predictive power on unseen samples. For this, we capitalize on the fact that connectomes (i.e., their adjacency matrices) lie in the symmetric positive definite (SPD) matrix cone. Our results on full-scale and verbal IQ prediction outperforms comparison methods in autism spectrum disorder cohorts and achieves a competitive performance for neurotypical subjects using 3-fold cross-validation. Furthermore, we show that our sample selection approach generalizes to other learning-based methods, which shows its usefulness beyond our GNN architecture.

Martin Hanik, Mehmet Arif DemirtaƟ, Mohammed Amine Gharsallaoui, Islem Rekik

2021-06-17

General General

MatES: Web-based Forward Chaining Expert System for Maternal Care

ArXiv Preprint

The solution to prevent maternal complications are known and preventable by trained health professionals. But in countries like Ethiopia where the patient to physician ratio is 1 doctor to 1000 patients, maternal mortality and morbidity rate is high. To fill the gap of highly trained health professionals, Ethiopia introduced health extension programs. Task shifting to health extension workers (HEWs) contributed in decreasing mortality and morbidity rate in Ethiopia. Knowledge-gap has been one of the major challenges to HEWs. The reasons are trainings are not given in regular manner, there is no midwife, gynecologists or doctors around for consultation, and all guidelines are paper-based which are easily exposed to damage. In this paper, we describe the design and implementation of a web-based expert system for maternal care. We only targeted the major 10 diseases and complication of maternal health issues seen in Sub-Saharan Africa. The expert system can be accessed through the use of web browsers from computers as well as smart phones. Forward chaining rule-based expert system is used in order to give suggestions and create a new knowledge from the knowledge-base. This expert system can be used to train HEWs in the field of maternal health. Keywords: expert system, maternal care, forward-chaining, rule-based expert system, PHLIPS

Haile Misgna, Moges Ahmed, Anubhav Kumar

2021-06-17