Related papers: Overlearning Reveals Sensitive Attributes

Speakers' referential expressions often depart from communicative ideals in ways that help illuminate the nature of pragmatic language use. Patterns of overmodification, in which a speaker uses a modifier that is redundant given their…

Observational learning is a type of learning that occurs as a function of observing, retaining and possibly replicating or imitating the behaviour of another agent. It is a core mechanism appearing in various instances of social learning…

Pretrained Language Models (LMs) memorize a vast amount of knowledge during initial pretraining, including information that may violate the privacy of personal lives and identities. Previous work addressing privacy issues for language…

Deep neural networks are increasingly deployed for scene analytics, including to evaluate the attention and reaction of people exposed to out-of-home advertisements. However, the features extracted by a deep neural network that was trained…

In supervised learning, it is known that overparameterized neural networks with one hidden layer provably and efficiently learn and generalize, when trained using stochastic gradient descent with a sufficiently small learning rate and…

Exposure bias describes the phenomenon that a language model trained under the teacher forcing schema may perform poorly at the inference stage when its predictions are conditioned on its previous predictions unseen from the training…

Decision analysis deals with modeling and enhancing decision processes. A principal challenge in improving behavior is in obtaining a transparent description of existing behavior in the first place. In this paper, we develop an expressive,…

Often, what is termed algorithmic bias in machine learning will be due to historic bias in the training data. But sometimes the bias may be introduced (or at least exacerbated) by the algorithm itself. The ways in which algorithms can…

Large Language Models (LLMs) have a privacy concern because they memorize training data (including personally identifiable information (PII) like emails and phone numbers) and leak it during inference. A company can train an LLM on its…

Do very high accuracies of deep networks suggest pride of effective AI or are deep networks prejudiced? Do they suffer from in-group biases (own-race-bias and own-age-bias), and mimic the human behavior? Is in-group specific information…

"Benign overfitting", where classifiers memorize noisy training data yet still achieve a good generalization performance, has drawn great attention in the machine learning community. To explain this surprising phenomenon, a series of works…

This work explores the biases in learning processes based on deep neural network architectures. We analyze how bias affects deep learning processes through a toy example using the MNIST database and a case study in gender detection from…

We investigate the training dynamics of deep classifiers by examining how hierarchical relationships between classes evolve during training. Through extensive experiments, we argue that the learning process in classification problems can be…

This work proposes a novel privacy-preserving neural network feature representation to suppress the sensitive information of a learned space while maintaining the utility of the data. The new international regulation for personal data…

High-performance visual recognition systems generally require a large collection of labeled images to train. The expensive data curation can be an obstacle for improving recognition performance. Sharing more data allows training for better…

Neural networks achieve the state-of-the-art in image classification tasks. However, they can encode spurious variations or biases that may be present in the training data. For example, training an age predictor on a dataset that is not…

Recent years have witnessed significant progresses in deep Reinforcement Learning (RL). Empowered with large scale neural networks, carefully designed architectures, novel training algorithms and massively parallel computing devices,…

Large language models (LLMs) exhibit cognitive biases -- systematic tendencies of irrational decision-making, similar to those seen in humans. Prior work has found that these biases vary across models and can be amplified by instruction…

It is widely believed that the success of deep networks lies in their ability to learn a meaningful representation of the features of the data. Yet, understanding when and how this feature learning improves performance remains a challenge:…

Machine learning models often learn to make predictions that rely on sensitive social attributes like gender and race, which poses significant fairness risks, especially in societal applications, such as hiring, banking, and criminal…