Machine unlearning is the task of updating a trained model to forget specific training data without retraining from scratch. In this paper, we investigate how unlearning of deep neural networks (DNNs) is affected by the model parameterization level, which corresponds here to the DNN width. We define validation-based tuning for several unlearning methods from the recent literature, and show how these methods perform differently depending on (i) the DNN parameterization level, (ii) the unlearning goal (unlearned data privacy or bias removal), (iii) whether the unlearning method explicitly uses the unlearned examples. Our results show that unlearning excels on overparameterized models, in terms of balancing between generalization and achieving the unlearning goal; although for bias removal this requires the unlearning method to use the unlearned examples. We further elucidate our error-based analysis by measuring how much the unlearning changes the classification decision regions in the proximity of the unlearned examples, and avoids changing them elsewhere. By this we show that the unlearning success for overparameterized models stems from the ability to delicately change the model functionality in small regions in the input space while keeping much of the model functionality unchanged.

With the vast development and employment of artificial intelligence applications, research into the fairness of these algorithms has been increased. Specifically, in the natural language processing domain, it has been shown that social biases persist in word embeddings and are thus in danger of amplifying these biases when used. As an example of social bias, religious biases are shown to persist in word embeddings and the need for its removal is highlighted. This paper investigates the state-of-the-art multiclass debiasing techniques: Hard debiasing, SoftWEAT debiasing and Conceptor debiasing. It evaluates their performance when removing religious bias on a common basis by quantifying bias removal via the Word Embedding Association Test (WEAT), Mean Average Cosine Similarity (MAC) and the Relative Negative Sentiment Bias (RNSB). By investigating the religious bias removal on three widely used word embeddings, namely: Word2Vec, GloVe, and ConceptNet, it is shown that the preferred method is ConceptorDebiasing. Specifically, this technique manages to decrease the measured religious bias on average by 82,42%, 96,78% and 54,76% for the three word embedding sets respectively.

With the ever-increasing cases of hate spread on social media platforms, it is critical to design abuse detection mechanisms to proactively avoid and control such incidents. While there exist methods for hate speech detection, they stereotype words and hence suffer from inherently biased training. Bias removal has been traditionally studied for structured datasets, but we aim at bias mitigation from unstructured text data. In this paper, we make two important contributions. First, we systematically design methods to quantify the bias for any model and propose algorithms for identifying the set of words which the model stereotypes. Second, we propose novel methods leveraging knowledge-based generalizations for bias-free learning. Knowledge-based generalization provides an effective way to encode knowledge because the abstraction they provide not only generalizes content but also facilitates retraction of information from the hate speech detection classifier, thereby reducing the imbalance. We experiment with multiple knowledge generalization policies and analyze their effect on general performance and in mitigating bias. Our experiments with two real-world datasets, a Wikipedia Talk Pages dataset (WikiDetox) of size ~96k and a Twitter dataset of size ~24k, show that the use of knowledge-based generalizations results in better performance by forcing the classifier to learn from generalized content. Our methods utilize existing knowledge-bases and can easily be extended to other tasks

Facial recognition tools have significant error rates that differ by race. An AI hiring tool from Amazon "learned" gender bias against women and favored male candidates. We know diversity bias is rampant in artificial intelligence. But decisions made based on prejudiced AI systems aren't just an ethical dilemma; they're a financial one. The more unbiased a system, the more likely it is to maximize profits, make better hiring or selling recommendations and provide accurate risk predictions.