15 accepted papers
Popular text-to-image (T2I) systems are trained on web-scraped data, which is heavily Amero and Euro-centric, underrepresenting the cultures of the Global South. To analyze these biases, we introduce CuRe, a novel and scalable benchmarking and scoring suite for cultural representativeness that lever…
This paper investigates metric learning in a Reproducing Kernel Hilbert Space (RKHS) based on a set of random triplet comparisons in the form of *"Do you think item h is more similar to item i or item j?"* indicating similarity and differences between various items. The goal is to learn a metric in
Foundation models trained on internet-scale data benefit from extensive alignment to human preferences before deployment. However, existing methods typically assume a homogeneous preference shared by all individuals, overlooking the diversity inherent in human values. In this work, we propose a gene…
Modern semi-supervised learning (SSL) methods rely on pseudolabeling and consistency regularization. Pseudolabeling is typically performed by comparing the model's confidence scores and a predefined threshold. While several heuristics have been proposed to improve threshold selection, the underlyin…
Ideal point based preference learning using pairwise comparisons of type "Do you prefer a or b?" has emerged as a powerful tool for understanding how we make preferences. Existing preference learning approaches assume homogeneity and focus on learning preference on average over the population or req…
Text-to-image diffusion models have achieved widespread popularity due to their unprecedented image generation capability. In particular, their ability to synthesize and modify human faces has spurred research into using generated face images in both training data augmentation and model performance…
We study metric learning from preference comparisons under the ideal point model, in which a user prefers an item over another if it is closer to their latent ideal item. These items are embedded into $\mathbb{R}^d$ equipped with an unknown Mahalanobis distance shared across users. While recent work…
Auto-labeling is an important family of techniques that produce labeled training sets with minimum manual annotation. A prominent variant, threshold-based auto-labeling (TBAL), works by finding thresholds on a model's confidence scores above which it can accurately automatically label unlabeled data…
Robustness to out-of-distribution (OOD) samples is crucial for the safe deployment of machine learning models in the open world. Recent works have focused on designing scoring functions to quantify OOD uncertainty. Setting appropriate thresholds for these scoring functions for OOD detection is chall…
Creating large-scale high-quality labeled datasets is a major bottleneck in supervised machine learning workflows. Threshold-based auto-labeling (TBAL), where validation data obtained from humans is used to find a confidence threshold above which the data is machine-labeled, reduces reliance on manu…
This paper investigates simultaneous preference and metric learning from a crowd of respondents. A set of items represented by $d$-dimensional feature vectors and paired comparisons of the form ``item $i$ is preferable to item $j$'' made by each user is given. Our model jointly learns a distance met…
We study the problem of estimating the distribution of effect sizes (the mean of the test statistic under the alternate hypothesis) in a multiple testing setting. Knowing this distribution allows us to calculate the power (type II error) of any experimental design. We show that it is possible to est…
Consider a setting with $N$ independent individuals, each with an unknown parameter, $p_i \in [0, 1]$ drawn from some unknown distribution $P^\star$. After observing the outcomes of $t$ independent Bernoulli trials, i.e., $X_i \sim \text{Binomial}(t, p_i)$ per individual, our objective is to accurat…
We consider the problem of crowdsourced clustering of a set of items based on queries of the similarity of triple of objects. Such an approach, called triangle queries, was proposed in [1], where it was shown that, for a fixed query budget, it outperforms clustering based on edge queries (i.e, compa…
We consider the task of clustering items using answers from non-expert crowd workers. In such cases, the workers are often not able to label the items directly, however, it is reasonable to assume that they can compare items and judge whether they are similar or not. An important question is what qu…