Related papers: Identifying and Mitigating Gender Bias in Hyperbol…
Models such as Word2Vec and GloVe construct word embeddings based on the co-occurrence probability $P(i,j)$ of words $i$ and $j$ in text corpora. The resulting vectors $W_i$ not only group semantically similar words but also exhibit a…
Online texts -- across genres, registers, domains, and styles -- are riddled with human stereotypes, expressed in overt or subtle ways. Word embeddings, trained on these texts, perpetuate and amplify these stereotypes, and propagate biases…
Complementary to finding good general word embeddings, an important question for representation learning is to find dynamic word embeddings, e.g., across time or domain. Current methods do not offer a way to use or predict information on…
Humans have entered the age of algorithms. Each minute, algorithms shape countless preferences from suggesting a product to a potential life partner. In the marketplace algorithms are trained to learn consumer preferences from customer…
Word2Vec is the most popular model for word representation and has been widely investigated in literature. However, its noise distribution for negative sampling is decided by empirical trials and the optimality has always been ignored. We…
Object detection, for the most part, has been formulated in the euclidean space, where euclidean or spherical geodesic distances measure the similarity of an image region to an object class prototype. In this work, we study whether a…
Gender bias in language models has gained increasing attention in the field of natural language processing. Encoder-based transformer models, which have achieved state-of-the-art performance in various language tasks, have been shown to…
Non-contextual word embedding models have been shown to inherit human-like stereotypical biases of gender, race and religion from the training corpora. To counter this issue, a large body of research has emerged which aims to mitigate these…
Learning generalizable self-supervised graph representations for downstream tasks is challenging. To this end, Contrastive Learning (CL) has emerged as a leading approach. The embeddings of CL are arranged on a hypersphere where similarity…
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…
Probabilistic Latent Variable Models (LVMs) excel at modeling complex, high-dimensional data through lower-dimensional representations. Recent advances show that equipping these latent representations with a Riemannian metric unlocks…
In recent years, word embeddings have been widely used to measure biases in texts. Even if they have proven to be effective in detecting a wide variety of biases, metrics based on word embeddings lack transparency and interpretability. We…
Vision-language models are growing in popularity and public visibility to generate, edit, and caption images at scale; but their outputs can perpetuate and amplify societal biases learned during pre-training on uncurated image-text pairs…
Metric learning plays a critical role in training image retrieval and classification. It is also a key algorithm in representation learning, e.g., for feature learning and its alignment in metric space. Hyperbolic embedding has been…
Contextualized word embeddings have been replacing standard embeddings as the representational knowledge source of choice in NLP systems. Since a variety of biases have previously been found in standard word embeddings, it is crucial to…
Hyperbolic spaces, which have the capacity to embed tree structures without distortion owing to their exponential volume growth, have recently been applied to machine learning to better capture the hierarchical nature of data. In this…
Text corpora are widely used resources for measuring societal biases and stereotypes. The common approach to measuring such biases using a corpus is by calculating the similarities between the embedding vector of a word (like nurse) and the…
Distributed word embeddings such as Word2Vec and GloVe have been widely adopted in industrial context settings. Major technical applications of GloVe include recommender systems and natural language processing. The fundamental theory behind…
Several prior studies have suggested that word frequency biases can cause the Bert model to learn indistinguishable sentence embeddings. Contrastive learning schemes such as SimCSE and ConSERT have already been adopted successfully in…
Clustering is a fundamental unsupervised learning task for uncovering patterns in data. While Gaussian Blurring Mean Shift (GBMS) has proven effective for identifying arbitrarily shaped clusters in Euclidean space, it struggles with…