February 25, 2024

We are creating some awesome events for you. Kindly bear with us.

Improving Fairness in Machine Learning Models

MIT researchers have found that machine-learning models that are popular for image recognition tasks actually encode bias when trained on unbalanced data. This bias within the model is impossible to fix later on, even with state-of-the-art fairness-boosting techniques, and even when retraining the model with a balanced dataset.

So, the researchers came up with a technique to introduce fairness directly into the model’s internal representation itself. This enables the model to produce fair outputs even if it is trained on unfair data, which is especially important because there are very few well-balanced datasets for machine learning. The solution they developed not only leads to models that make more balanced predictions but also improves their performance on downstream tasks like facial recognition and animal species classification.

In machine learning, it is common to blame the data for bias in models. But we don’t always have balanced data. So, we need to come up with methods that actually fix the problem with imbalanced data.

– Natalie Dullerud, Lead Author

The machine-learning technique the researchers studied is known as deep metric learning, which is a broad form of representation learning. In deep metric learning, a neural network learns the similarity between objects by mapping similar photos close together and dissimilar photos far apart. During training, this neural network maps images in an “embedding space” where a similarity metric between photos corresponds to the distance between them.

For example, if a deep metric learning model is being used to classify bird species, it will map photos of golden finches together in one part of the embedding space and cardinals together in another part of the embedding space. Once trained, the model can effectively measure the similarity of new images it hasn’t seen before. It would learn to cluster images of an unseen bird species close together, but farther from cardinals or golden finches within the embedding space.

The researchers defined two ways that a similarity metric can be unfair. Using the example of facial recognition, the metric will be unfair if it is more likely to embed individuals with darker-skinned faces closer to each other, even if they are not the same person, than it would if those images were people with lighter-skinned faces. Second, it will be unfair if the features it learns for measuring similarity are better for the majority group than for the minority group.

The researchers’ solution, called Partial Attribute Decorrelation (PARADE), involves training the model to learn a separate similarity metric for a sensitive attribute, like skin tone, and then decorrelating the skin tone similarity metric from the targeted similarity metric. If the model is learning the similarity metrics of different human faces, it will learn to map similar faces close together and dissimilar faces far apart using features other than skin tone.

Their method is applicable to many situations because the user can control the amount of decorrelation between similarity metrics. For instance, if the model will be diagnosing breast cancer from mammogram images, a clinician likely wants some information about biological sex to remain in the final embedding space because it is much more likely that women will have breast cancer than men.

They tested their method on two tasks, facial recognition and classifying bird species, and found that it reduced performance gaps caused by bias, both in the embedding space and in the downstream task, regardless of the dataset they used. Moving forward, the researchers are interested in studying how to force a deep metric learning model to learn good features in the first place.


Qlik’s vision is a data-literate world, where everyone can use data and analytics to improve decision-making and solve their most challenging problems. A private company, Qlik offers real-time data integration and analytics solutions, powered by Qlik Cloud, to close the gaps between data, insights and action. By transforming data into Active Intelligence, businesses can drive better decisions, improve revenue and profitability, and optimize customer relationships. Qlik serves more than 38,000 active customers in over 100 countries.


CTC Global Singapore, a premier end-to-end IT solutions provider, is a fully owned subsidiary of ITOCHU Techno-Solutions Corporation (CTC) and ITOCHU Corporation.

Since 1972, CTC has established itself as one of the country’s top IT solutions providers. With 50 years of experience, headed by an experienced management team and staffed by over 200 qualified IT professionals, we support organizations with integrated IT solutions expertise in Autonomous IT, Cyber Security, Digital Transformation, Enterprise Cloud Infrastructure, Workplace Modernization and Professional Services.

Well-known for our strengths in system integration and consultation, CTC Global proves to be the preferred IT outsourcing destination for organizations all over Singapore today.


Planview has one mission: to build the future of connected work. Our solutions enable organizations to connect the business from ideas to impact, empowering companies to accelerate the achievement of what matters most. Planview’s full spectrum of Portfolio Management and Work Management solutions creates an organizational focus on the strategic outcomes that matter and empowers teams to deliver their best work, no matter how they work. The comprehensive Planview platform and enterprise success model enables customers to deliver innovative, competitive products, services, and customer experiences. Headquartered in Austin, Texas, with locations around the world, Planview has more than 1,300 employees supporting 4,500 customers and 2.6 million users worldwide. For more information, visit www.planview.com.


SIRIM is a premier industrial research and technology organisation in Malaysia, wholly-owned by the Minister​ of Finance Incorporated. With over forty years of experience and expertise, SIRIM is mandated as the machinery for research and technology development, and the national champion of quality. SIRIM has always played a major role in the development of the country’s private sector. By tapping into our expertise and knowledge base, we focus on developing new technologies and improvements in the manufacturing, technology and services sectors. We nurture Small Medium Enterprises (SME) growth with solutions for technology penetration and upgrading, making it an ideal technology partner for SMEs.


HashiCorp provides infrastructure automation software for multi-cloud environments, enabling enterprises to unlock a common cloud operating model to provision, secure, connect, and run any application on any infrastructure. HashiCorp tools allow organizations to deliver applications faster by helping enterprises transition from manual processes and ITIL practices to self-service automation and DevOps practices. 


IBM is a leading global hybrid cloud and AI, and business services provider. We help clients in more than 175 countries capitalize on insights from their data, streamline business processes, reduce costs and gain the competitive edge in their industries. Nearly 3,000 government and corporate entities in critical infrastructure areas such as financial services, telecommunications and healthcare rely on IBM’s hybrid cloud platform and Red Hat OpenShift to affect their digital transformations quickly, efficiently and securely. IBM’s breakthrough innovations in AI, quantum computing, industry-specific cloud solutions and business services deliver open and flexible options to our clients. All of this is backed by IBM’s legendary commitment to trust, transparency, responsibility, inclusivity and service.

Send this to a friend