PRESS-NEWS.org - Press Release Distribution
PRESS RELEASES DISTRIBUTION

New machine learning model could remove bias from social network connections

2021-03-12
(Press-News.org) UNIVERSITY PARK, Pa. -- Did you ever wonder how social networking applications like Facebook and LinkedIn make recommendations on the people you should friend or pages you should follow?

Behind the scenes are machine learning models that classify nodes based on the data they contain about users -- for example, their level of education, location or political affiliation. The models then use these classifications to recommend people and pages to each user. But there is significant bias in the recommendations made by these models -- known as graph neural networks (GNNs) -- as they rely on user features that are highly related to sensitive attributes such as gender or skin color.

Recognizing that the majority of users are reluctant to publicize their sensitive attributes, researchers at the Penn State College of Information Sciences and Technology have developed a novel framework which estimates sensitive attributes to help GNNs make fair recommendations.

The team found that their model, called FairGNN, maintains high performance on node classification using limited, user-supplied sensitive information, while at the same time reducing bias.

"It has been widely reported that people tend to build relationships with those sharing the same sensitive attributes such as ages and regions," said Enyan Dai, doctoral candidate in informatics and lead author on the research paper. "There are some existing machine learning models that aim to eliminate bias, but they require people's sensitive attributes to make them fair and accurate. We are proposing to apply another model based on the very few sensitive attributes that we have (and instead look at other provided information) which could provide us very good insight to give fair predictions toward sensitive attributes such as your gender and skin color."

The researchers trained their model with two real-world datasets: user profiles on Pokec, a popular social network in Slovakia, similar to Facebook and Twitter; and a dataset of approximately 400 NBA basketball players. In the Pokec dataset, they treated the region in which each user was from as the sensitive attribute, and set the classification task to predict the working field of the users. In the NBA data, they identified players as those in the U.S. and those overseas, using location as the sensitive attribute with the classification task to predict whether the salary of each player is over the median.

They then used the same datasets to test their model with other state-of-the-art methods for fair classification. First, they evaluated FairGNN in terms of fairness and classification performance. Then, they performed "ablation studies" -- which remove certain components of the model to test the significance of each component to the overall system -- to further strengthen the model. They then tested whether FairGNN is effective when different amounts of sensitive attributes are provided in the training set.

"Our experiment shows that the classification performance doesn't decrease," said Suhang Wang, assistant professor of information sciences and technology and principal investigator on the project. "But in terms of fairness, we can make the model much more fair."

According to the researchers, their framework could make an impact for other real-world use cases.

"Our findings could be useful in applications, such as job applicant rankings, crime detection or in financial loan applications," said Wang. "But those are domains where we don't want to introduce bias. So we want to give accurate predictions while maintaining fairness."

Added Dai, "[If] this fair machine learning model could be introduced in these applications, we will have more fair data and this problem would be gradually dissolved."

INFORMATION:

Dai and Wang presented their work this week at the virtual ACM International Conference on Web Search and Data Mining, with support from the National Science Foundation and the Global Research Outreach program of Samsung Advanced Institute of Technology.



ELSE PRESS RELEASES FROM THIS DATE:

Study finds adolescents with autism may engage neural control systems differently

2021-03-12
A new study by UC Davis MIND Institute researchers suggests that executive control differences in autism spectrum disorder (ASD) may be the result of a unique approach, rather than an impairment. Executive control difficulties are common in individuals with autism and are associated with challenges completing tasks and managing time. The study, published in Biological Psychiatry: Cognitive Neuroscience and Neuroimaging, sought to tease out whether these difficulties represent a disruption in proactive executive control (engaged and maintained before a ...

Use of perovskite will be a key feature of the next generation of electronic appliances

Use of perovskite will be a key feature of the next generation of electronic appliances
2021-03-12
Quantum dots are manmade nanoparticles of semiconducting material comprising only a few thousand atoms. Because of the small number of atoms, a quantum dot's properties lie between those of single atoms or molecules and bulk material with a huge number of atoms. By changing the nanoparticles' size and shape, it is possible to fine-tune their electronic and optical properties - how electrons bond and move through the material, and how light is absorbed and emitted by it. Thanks to increasingly refined control of the nanoparticles' size and shape, the number ...

Artificial intelligence calculates suicide attempt risk

Artificial intelligence calculates suicide attempt risk
2021-03-12
A machine learning algorithm that predicts suicide attempt recently underwent a prospective trial at the institution where it was developed, Vanderbilt University Medical Center. Over the 11 consecutive months concluding in April 2020, predictions ran silently in the background as adult patients were seen at VUMC. The algorithm, dubbed the Vanderbilt Suicide Attempt and Ideation Likelihood (VSAIL) model, uses routine information from electronic health records (EHRs) to calculate 30-day risk of return visits for suicide attempt, and, by extension, suicidal ideation. Suicide has been on the rise in the U.S. for a generation ...

Association of acute symptoms of COVID-19, symptoms of depression in adults

2021-03-12
What The Study Did: Researchers investigated whether acute COVID-19 symptoms are associated with the probability of subsequent depressive symptoms. Authors: Roy H. Perlis, M.D., M.Sc., of the Massachusetts General Hospital in Boston, is the corresponding author. To access the embargoed study:  Visit our For The Media website at this link https://media.jamanetwork.com/ (doi:10.1001/jamanetworkopen.2021.3223) Editor's Note: Editor's Note: The article includes conflict of interest and funding/support disclosures. Please see the article for additional information, ...

Well-child visits with out-of-pocket costs before, after ACA

2021-03-12
What The Study Did: National claims data were used to look at changes in well-child care visits with out-of-pocket costs before and after passage of the Affordable Care Act. Authors: Paul R. Shafer, Ph.D., of Boston University, is the corresponding author. To access the embargoed study: Visit our For The Media website at this link https://media.jamanetwork.com/ (doi:10.1001/jamanetworkopen.2021.1248) Editor's Note: Editor's Note: The article includes conflicts of interest disclosures. Please see the article for additional information, including other authors, author contributions and affiliations, conflict of interest and financial disclosures, and funding ...

Association between preterm birth, psychotropic drug use in adolescence, young adulthood

2021-03-12
What The Study Did: Researchers compared rates of psychotropic drug prescriptions during adolescence and young adulthood between individuals born preterm and at term. Authors: Christine S. Bachmann, M.D., of the Norwegian University of Science and Technology in Trondheim, Norway, is the corresponding author. To access the embargoed study: Visit our For The Media website at this link https://media.jamanetwork.com/ (doi:10.1001/jamanetworkopen.2021.1420) Editor's Note: Editor's Note: The article includes funding/support disclosures. Please see the article for additional information, including other authors, ...

Poor survival after heart attack linked to excess levels of signaling protein in heart

2021-03-12
(Philadelphia, PA) - About 6.2 million Americans suffer from heart failure, an incurable disease with a staggering mortality rate - some 40 percent of patients die within five years of diagnosis. Heart failure is one form of heart disease, for which new therapies are desperately needed. Now, in new work, scientists at the Lewis Katz School of Medicine (LKSOM) at Temple University identify a path to a promising novel therapeutic strategy, taking aim at a molecule in the heart known as G protein-coupled receptor kinase 5 (GRK5). In a study published online in the journal Cardiovascular Research, the scientists show in mice that reducing GRK5 levels can significantly improve survival ...

Astronomers detect a black hole on the move

Astronomers detect a black hole on the move
2021-03-12
Scientists have long theorized that supermassive black holes can wander through space--but catching them in the act has proven difficult. Now, researchers at the Center for Astrophysics | Harvard & Smithsonian have identified the clearest case to date of a supermassive black hole in motion. Their results are published today in the Astrophysical Journal. "We don't expect the majority of supermassive black holes to be moving; they're usually content to just sit around," says Dominic Pesce, an astronomer at the Center for Astrophysics who led the study. "They're just so heavy that it's tough to get them going. Consider how much more ...

Study uncovers clues to COVID-19 using imaging

Study uncovers clues to COVID-19 using imaging
2021-03-12
Since the pandemic hit, researchers have been uncovering ways COVID-19 impacts other parts of the body, besides the lungs. Now, for the first time, a visual correlation has been found between the severity of the disease in the lungs using CT scans and the severity of effects on patient's brains, using MRI scans. This research is published in the American Journal of Neuroradiology. It will be presented at the 59th annual meeting of the American Society of Neuroradiology (ASNR) and has also been selected as a semifinalist for that organization's Cornelius Dyke Award. The results show that by looking at lung CT scans of patients diagnosed with COVID-19, physicians may be able to predict just how badly they'll experience other ...

Yeast epigenome map reveals details of gene regulation

2021-03-12
ITHACA, N.Y. - A new Penn State and Cornell study describes an effort to produce the most comprehensive and high-resolution map yet of chromosome architecture and gene regulation in yeast, a major step toward improving understanding of development, evolution and environmental responses in higher organisms. Specifically, the study mapped precise binding sites of more than 400 different chromosomal proteins in the yeast genome, most of which regulate the expression of genes. Yeast cells provide a simple model system with 6,000 genes, most of which are found in other organisms, including humans, making them excellent candidates for studying fundamental genetics and complex biological pathways. The paper, "A High-Resolution Protein Architecture of the Budding Yeast ...

LAST 30 PRESS RELEASES:

Scientists unlock secrets behind flowering of the king of fruits

Texas A&M researchers illuminate the mysteries of icy ocean worlds

Prosthetic material could help reduce infections from intravenous catheters

Can the heart heal itself? New study says it can

Microscopic discovery in cancer cells could have a big impact

Rice researchers take ‘significant leap forward’ with quantum simulation of molecular electron transfer

Breakthrough new material brings affordable, sustainable future within grasp

How everyday activities inside your home can generate energy

Inequality weakens local governance and public satisfaction, study finds

Uncovering key molecular factors behind malaria’s deadliest strain

UC Davis researchers help decode the cause of aggressive breast cancer in women of color

Researchers discovered replication hubs for human norovirus

SNU researchers develop the world’s most sensitive flexible strain sensor

Tiny, wireless antennas use light to monitor cellular communication

Neutrality has played a pivotal, but under-examined, role in international relations, new research shows

Study reveals right whales live 130 years — or more

Researchers reveal how human eyelashes promote water drainage

Pollinators most vulnerable to rising global temperatures are flies, study shows

DFG to fund eight new research units

Modern AI systems have achieved Turing's vision, but not exactly how he hoped

Quantum walk computing unlocks new potential in quantum science and technology

Construction materials and household items are a part of a long-term carbon sink called the “technosphere”

First demonstration of quantum teleportation over busy Internet cables

Disparities and gaps in breast cancer screening for women ages 40 to 49

US tobacco 21 policies and potential mortality reductions by state

AI-driven approach reveals hidden hazards of chemical mixtures in rivers

Older age linked to increased complications after breast reconstruction

ESA and NASA satellites deliver first joint picture of Greenland Ice Sheet melting

Early detection model for pancreatic necrosis improves patient outcomes

Poor vascular health accelerates brain ageing

[Press-News.org] New machine learning model could remove bias from social network connections