Learning fair models and representations

Machine learning based systems and products are reaching society at large in many aspects of everyday life, including financial lending, online advertising, pretrial and immigration detention, child maltreatment screening, health care, social services, and education. This phenomenon has been accompanied by an increase in concern about the ethical issues that may rise from the adoption of these technologies. In response to this concern, a new area of machine learning has recently emerged that studies how to address disparate treatment caused by algorithmic errors and bias in the data. The central question is how to ensure that the learned model does not treat subgroups in the population unfairly. While the design of solutions to this issue requires an interdisciplinary effort, fundamental progress can only be achieved through a radical change in the machine learning paradigm. In this work, we will describe the state of the art on algorithmic fairness using statistical learning theory, machine learning, and deep learning approaches that are able to learn fair models and data representation.

Download Full-text

Supervised learning for the detection of negation and of its scope in French and Brazilian Portuguese biomedical corpora

Natural Language Engineering ◽

10.1017/s1351324920000352 ◽

2020 ◽

pp. 1-21 ◽

Cited By ~ 2

Author(s):

Clément Dalloux ◽

Vincent Claveau ◽

Natalia Grabar ◽

Lucas Emanuel Silva Oliveira ◽

Claudia Maria Cabral Moro ◽

...

Keyword(s):

Machine Learning ◽

Information Extraction ◽

State Of The Art ◽

Automatic Detection ◽

Brazilian Portuguese ◽

Supervised Machine Learning ◽

Biomedical Domain ◽

Learning Approaches ◽

Cross Domain ◽

Automatic Methods

Abstract Automatic detection of negated content is often a prerequisite in information extraction systems in various domains. In the biomedical domain especially, this task is important because negation plays an important role. In this work, two main contributions are proposed. First, we work with languages which have been poorly addressed up to now: Brazilian Portuguese and French. Thus, we developed new corpora for these two languages which have been manually annotated for marking up the negation cues and their scope. Second, we propose automatic methods based on supervised machine learning approaches for the automatic detection of negation marks and of their scopes. The methods show to be robust in both languages (Brazilian Portuguese and French) and in cross-domain (general and biomedical languages) contexts. The approach is also validated on English data from the state of the art: it yields very good results and outperforms other existing approaches. Besides, the application is accessible and usable online. We assume that, through these issues (new annotated corpora, application accessible online, and cross-domain robustness), the reproducibility of the results and the robustness of the NLP applications will be augmented.

Download Full-text

Inference of an Integrative, Executable Network for Rheumatoid Arthritis Combining Data-Driven Machine Learning Approaches and a State-of-the-Art Mechanistic Disease Map

Journal of Personalized Medicine ◽

10.3390/jpm11080785 ◽

2021 ◽

Vol 11 (8) ◽

pp. 785

Author(s):

Quentin Miagoux ◽

Vidisha Singh ◽

Dereck de Mézquita ◽

Valerie Chaudru ◽

Mohamed Elati ◽

...

Keyword(s):

Rheumatoid Arthritis ◽

Machine Learning ◽

State Of The Art ◽

Biological Information ◽

Response To Treatment ◽

Patient Specific ◽

Learning Approaches ◽

Data Types ◽

Disease Heterogeneity ◽

Combining Data

Rheumatoid arthritis (RA) is a multifactorial, complex autoimmune disease that involves various genetic, environmental, and epigenetic factors. Systems biology approaches provide the means to study complex diseases by integrating different layers of biological information. Combining multiple data types can help compensate for missing or conflicting information and limit the possibility of false positives. In this work, we aim to unravel mechanisms governing the regulation of key transcription factors in RA and derive patient-specific models to gain more insights into the disease heterogeneity and the response to treatment. We first use publicly available transcriptomic datasets (peripheral blood) relative to RA and machine learning to create an RA-specific transcription factor (TF) co-regulatory network. The TF cooperativity network is subsequently enriched in signalling cascades and upstream regulators using a state-of-the-art, RA-specific molecular map. Then, the integrative network is used as a template to analyse patients’ data regarding their response to anti-TNF treatment and identify master regulators and upstream cascades affected by the treatment. Finally, we use the Boolean formalism to simulate in silico subparts of the integrated network and identify combinations and conditions that can switch on or off the identified TFs, mimicking the effects of single and combined perturbations.

Download Full-text

From Characters to Time Intervals: New Paradigms for Evaluation and Neural Parsing of Time Normalizations

Transactions of the Association for Computational Linguistics ◽

10.1162/tacl_a_00025 ◽

2018 ◽

Vol 6 ◽

pp. 343-356 ◽

Cited By ~ 2

Author(s):

Egoitz Laparra ◽

Dongfang Xu ◽

Steven Bethard

Keyword(s):

Neural Network ◽

Machine Learning ◽

Comparative Analysis ◽

State Of The Art ◽

Learning Approaches ◽

Semantic Parsing ◽

Time Intervals ◽

Semantic Composition ◽

Previous State ◽

New Scoring

This paper presents the first model for time normalization trained on the SCATE corpus. In the SCATE schema, time expressions are annotated as a semantic composition of time entities. This novel schema favors machine learning approaches, as it can be viewed as a semantic parsing task. In this work, we propose a character level multi-output neural network that outperforms previous state-of-the-art built on the TimeML schema. To compare predictions of systems that follow both SCATE and TimeML, we present a new scoring metric for time intervals. We also apply this new metric to carry out a comparative analysis of the annotations of both schemes in the same corpus.

Download Full-text

Comparing Deep-Learning Architectures and Traditional Machine-Learning Approaches for Satire Identification in Spanish Tweets

Mathematics ◽

10.3390/math8112075 ◽

2020 ◽

Vol 8 (11) ◽

pp. 2075

Author(s):

Óscar Apolinario-Arzube ◽

José Antonio García-Díaz ◽

José Medina-Moreira ◽

Harry Luna-Aveiga ◽

Rafael Valencia-García

Keyword(s):

Machine Learning ◽

Deep Learning ◽

User Interfaces ◽

State Of The Art ◽

Learning Approaches ◽

Word Embeddings ◽

Linguistic Features ◽

Intended Meaning ◽

Language User ◽

Learning Architectures

Automatic satire identification can help to identify texts in which the intended meaning differs from the literal meaning, improving tasks such as sentiment analysis, fake news detection or natural-language user interfaces. Typically, satire identification is performed by training a supervised classifier for finding linguistic clues that can determine whether a text is satirical or not. For this, the state-of-the-art relies on neural networks fed with word embeddings that are capable of learning interesting characteristics regarding the way humans communicate. However, as far as our knowledge goes, there are no comprehensive studies that evaluate these techniques in Spanish in the satire identification domain. Consequently, in this work we evaluate several deep-learning architectures with Spanish pre-trained word-embeddings and compare the results with strong baselines based on term-counting features. This evaluation is performed with two datasets that contain satirical and non-satirical tweets written in two Spanish variants: European Spanish and Mexican Spanish. Our experimentation revealed that term-counting features achieved similar results to deep-learning approaches based on word-embeddings, both outperforming previous results based on linguistic features. Our results suggest that term-counting features and traditional machine learning models provide competitive results regarding automatic satire identification, slightly outperforming state-of-the-art models.

Download Full-text

Deep Machine Learning provides state-of-the-art performance in image-based plant phenotyping

10.1101/053033 ◽

2016 ◽

Cited By ~ 12

Author(s):

Michael P. Pound ◽

Alexandra J. Burgess ◽

Michael H. Wilson ◽

Jonathan A. Atkinson ◽

Marcus Griffiths ◽

...

Keyword(s):

Machine Learning ◽

Deep Learning ◽

Data Analysis ◽

Paradigm Shift ◽

State Of The Art ◽

Plant Phenotyping ◽

Learning Approaches ◽

Challenging Problem ◽

Feature Identification ◽

Art Performance

AbstractDeep learning is an emerging field that promises unparalleled results on many data analysis problems. We show the success offered by such techniques when applied to the challenging problem of image-based plant phenotyping, and demonstrate state-of-the-art results for root and shoot feature identification and localisation. We predict a paradigm shift in image-based phenotyping thanks to deep learning approaches.

Download Full-text

EEG Based Eye State Classification using Deep Belief Network and Stacked AutoEncoder

International Journal of Electrical and Computer Engineering (IJECE) ◽

10.11591/ijece.v6i6.12967 ◽

2016 ◽

Vol 6 (6) ◽

pp. 3131 ◽

Cited By ~ 4

Author(s):

Sanam Narejo ◽

Eros Pasero ◽

Farzana Kulsoom

Keyword(s):

Machine Learning ◽

State Of The Art ◽

Deep Belief Network ◽

Machine Learning Algorithms ◽

Learning Approaches ◽

Alternative Communication ◽

Eeg Signals ◽

Communication Interface ◽

Belief Network ◽

State Classification

<p>A Brain-Computer Interface (BCI) provides an alternative communication interface between the human brain and a computer. The Electroencephalogram (EEG) signals are acquired, processed and machine learning algorithms are further applied to extract useful information. During EEG acquisition, artifacts are induced due to involuntary eye movements or eye blink, casting adverse effects on system performance. The aim of this research is to predict eye states from EEG signals using Deep learning architectures and present improved classifier models. Recent studies reflect that Deep Neural Networks are trending state of the art Machine learning approaches. Therefore, the current work presents the implementation of Deep Belief Network (DBN) and Stacked AutoEncoders (SAE) as Classifiers with encouraging performance accuracy. One of the designed SAE models outperforms the performance of DBN and the models presented in existing research by an impressive error rate of 1.1% on the test set bearing accuracy of 98.9%. The findings in this study, may provide a contribution towards the state of the art performance on the problem of EEG based eye state classification.</p>

Download Full-text

An Introduction to Machine Learning Approaches for Biomedical Research

Frontiers in Medicine ◽

10.3389/fmed.2021.771607 ◽

2021 ◽

Vol 8 ◽

Author(s):

Juan Jovel ◽

Russell Greiner

Keyword(s):

Machine Learning ◽

Reinforcement Learning ◽

Biomedical Research ◽

Applied Research ◽

State Of The Art ◽

Learning Approaches ◽

Therapy Outcomes ◽

Computational Approaches ◽

Specific Goal ◽

Basic And Applied Research

Machine learning (ML) approaches are a collection of algorithms that attempt to extract patterns from data and to associate such patterns with discrete classes of samples in the data—e.g., given a series of features describing persons, a ML model predicts whether a person is diseased or healthy, or given features of animals, it predicts weather an animal is treated or control, or whether molecules have the potential to interact or not, etc. ML approaches can also find such patterns in an agnostic manner, i.e., without having information about the classes. Respectively, those methods are referred to as supervised and unsupervised ML. A third type of ML is reinforcement learning, which attempts to find a sequence of actions that contribute to achieving a specific goal. All of these methods are becoming increasingly popular in biomedical research in quite diverse areas including drug design, stratification of patients, medical images analysis, molecular interactions, prediction of therapy outcomes and many more. We describe several supervised and unsupervised ML techniques, and illustrate a series of prototypical examples using state-of-the-art computational approaches. Given the complexity of reinforcement learning, it is not discussed in detail here, instead, interested readers are referred to excellent reviews on that topic. We focus on concepts rather than procedures, as our goal is to attract the attention of researchers in biomedicine toward the plethora of powerful ML methods and their potential to leverage basic and applied research programs.

Download Full-text

Visual complexity modelling based on image features fusion of multiple kernels

PeerJ ◽

10.7717/peerj.7075 ◽

2019 ◽

Vol 7 ◽

pp. e7075 ◽

Cited By ~ 3

Author(s):

Carlos Fernandez-Lozano ◽

Adrian Carballal ◽

Penousal Machado ◽

Antonino Santos ◽

Juan Romero

Keyword(s):

Machine Learning ◽

Computational Models ◽

State Of The Art ◽

Visual Complexity ◽

Multiple Kernel Learning ◽

Human Mind ◽

Image Features ◽

Machine Learning Techniques ◽

Learning Approaches ◽

The Impact

Humans’ perception of visual complexity is often regarded as one of the key principles of aesthetic order, and is intimately related to the physiological, neurological and, possibly, psychological characteristics of the human mind. For these reasons, creating accurate computational models of visual complexity is a demanding task. Building upon on previous work in the field (Forsythe et al., 2011; Machado et al., 2015) we explore the use of Machine Learning techniques to create computational models of visual complexity. For that purpose, we use a dataset composed of 800 visual stimuli divided into five categories, describing each stimulus by 329 features based on edge detection, compression error and Zipf’s law. In an initial stage, a comparative analysis of representative state-of-the-art Machine Learning approaches is performed. Subsequently, we conduct an exhaustive outlier analysis. We analyze the impact of removing the extreme outliers, concluding that Feature Selection Multiple Kernel Learning obtains the best results, yielding an average correlation to humans’ perception of complexity of 0.71 with only twenty-two features. These results outperform the current state-of-the-art, showing the potential of this technique for regression.

Download Full-text

Stance Detection Benchmark: How Robust is Your Stance Detection?

KI - Künstliche Intelligenz ◽

10.1007/s13218-021-00714-w ◽

2021 ◽

Author(s):

Benjamin Schiller ◽

Johannes Daxenberger ◽

Iryna Gurevych

Keyword(s):

Machine Learning ◽

State Of The Art ◽

Learning Approaches ◽

Fake News ◽

Human Capabilities ◽

Task Learning ◽

Single Dataset ◽

Easy Integration ◽

Number Of Classes

AbstractStance detection (StD) aims to detect an author’s stance towards a certain topic and has become a key component in applications like fake news detection, claim validation, or argument search. However, while stance is easily detected by humans, machine learning (ML) models are clearly falling short of this task. Given the major differences in dataset sizes and framing of StD (e.g. number of classes and inputs), ML models trained on a single dataset usually generalize poorly to other domains. Hence, we introduce a StD benchmark that allows to compare ML models against a wide variety of heterogeneous StD datasets to evaluate them for generalizability and robustness. Moreover, the framework is designed for easy integration of new datasets and probing methods for robustness. Amongst several baseline models, we define a model that learns from all ten StD datasets of various domains in a multi-dataset learning (MDL) setting and present new state-of-the-art results on five of the datasets. Yet, the models still perform well below human capabilities and even simple perturbations of the original test samples (adversarial attacks) severely hurt the performance of MDL models. Deeper investigation suggests overfitting on dataset biases as the main reason for the decreased robustness. Our analysis emphasizes the need of focus on robustness and de-biasing strategies in multi-task learning approaches. To foster research on this important topic, we release the dataset splits, code, and fine-tuned weights.

Download Full-text

A computational method for drug sensitivity prediction of cancer cell lines based on various molecular information

PLoS ONE ◽

10.1371/journal.pone.0250620 ◽

2021 ◽

Vol 16 (4) ◽

pp. e0250620

Author(s):

Fatemeh Ahmadi Moughari ◽

Changiz Eslahchi

Keyword(s):

Machine Learning ◽

Cell Line ◽

Drug Sensitivity ◽

State Of The Art ◽

Computational Method ◽

Cancer Drug ◽

Learning Approaches ◽

Efficient Treatment ◽

Proposed Model ◽

Anti Cancer

Determining sensitive drugs for a patient is one of the most critical problems in precision medicine. Using genomic profiles of the tumor and drug information can help in tailoring the most efficient treatment for a patient. In this paper, we proposed a classification machine learning approach that predicts the sensitive/resistant drugs for a cell line. It can be performed by using both drug and cell line similarities, one of the cell line or drug similarities, or even not using any similarity information. This paper investigates the influence of using previously defined as well as two newly introduced similarities on predicting anti-cancer drug sensitivity. The proposed method uses max concentration thresholds for assigning drug responses to class labels. Its performance was evaluated using stratified five-fold cross-validation on cell line-drug pairs in two datasets. Assessing the predictive powers of the proposed model and three sets of methods, including state-of-the-art classification methods, state-of-the-art regression methods, and off-the-shelf classification machine learning approaches shows that the proposed method outperforms other methods. Moreover, The efficiency of the model is evaluated in tissue-specific conditions. Besides, the novel sensitive associations predicted by this model were verified by several supportive evidence in the literature and reliable database. Therefore, the proposed model can efficiently be used in predicting anti-cancer drug sensitivity. Material and implementation are available at https://github.com/fahmadimoughari/CDSML.

Download Full-text