In this paper, we leverage existing statistical methods to better understand feature learning from data. We tackle this by modifying the model-free variable selection method, Feature Ordering by Conditional Independence (FOCI), which is introduced in \cite{azadkia2021simple}. While FOCI is based on a non-parametric coefficient of conditional dependence, we introduce its parametric, differentiable approximation. With this approximate coefficient of correlation, we present a new algorithm called difFOCI, which is applicable to a wider range of machine learning problems thanks to its differentiable nature and learnable parameters. We present difFOCI in three contexts: (1) as a variable selection method with baseline comparisons to FOCI, (2) as a trainable model parametrized with a neural network, and (3) as a generic, widely applicable neural network regularizer, one that improves feature learning with better management of spurious correlations. We evaluate difFOCI on increasingly complex problems ranging from basic variable selection in toy examples to saliency map comparisons in convolutional networks. We then show how difFOCI can be incorporated in the context of fairness to facilitate classifications without relying on sensitive data.

Large language models (LLMs) are often fine-tuned for use on downstream tasks, though this can degrade capabilities learned during previous training. This phenomenon, often referred to as catastrophic forgetting, has important potential implications for the safety of deployed models. In this work, we first show that models trained on downstream tasks forget their safety tuning to a greater extent than models trained in the opposite order. Second, we show that forgetting disproportionately impacts safety information about certain groups. To quantify this phenomenon, we define a new metric we term biased forgetting. We conduct a systematic evaluation of the effects of task ordering on forgetting and apply mitigations that can help the model recover from the forgetting observed. We hope our findings can better inform methods for chaining the finetuning of LLMs in continual learning settings to enable training of safer and less toxic models.

Text toxicity detection systems exhibit significant biases, producing disproportionate rates of false positives on samples mentioning demographic groups. But what about toxicity detection in speech? To investigate the extent to which text-based biases are mitigated by speech-based systems, we produce a set of high-quality group annotations for the multilingual MuTox dataset, and then leverage these annotations to systematically compare speech- and text-based toxicity classifiers. Our findings indicate that access to speech data during inference supports reduced bias against group mentions, particularly for ambiguous and disagreement-inducing samples. Our results also suggest that improving classifiers, rather than transcription pipelines, is more helpful for reducing group bias. We publicly release our annotations and provide recommendations for future toxicity dataset construction.

Content Warning: This paper contains examples of offensive transphobic content. Natural-language assistants are designed to provide users with helpful responses while avoiding harmful outputs, largely achieved through alignment to human preferences. Yet there is limited understanding of whether alignment techniques may inadvertently perpetuate or even amplify harmful biases inherited from their pre-aligned base models. This issue is compounded by the choice of bias evaluation benchmarks in popular preference-finetuned models, which predominantly focus on dominant social categories, such as binary gender, thereby limiting insights into biases affecting underrepresented groups. Towards addressing this gap, we center transgender, nonbinary, and other gender-diverse identities to investigate how alignment procedures interact with pre-existing gender-diverse bias in LLMs. Our key contributions include: 1) a comprehensive survey of bias evaluation modalities across leading preference-finetuned LLMs, highlighting critical gaps in genderdiverse representation, 2) systematic evaluation of gender-diverse biases across 12 models spanning Direct Preference Optimization (DPO) stages, uncovering harms popular bias benchmarks fail to detect, and 3) a flexible framework for measuring harmful biases in implicit reward signals applicable to other social contexts. Our findings reveal that DPO-aligned models are particularly sensitive to supervised finetuning (SFT), and can amplify two forms of real-world gender-diverse harms from their base models: stigmatization and gender non-affirmative language. We conclude with recommendations tailored to DPO and broader alignment practices, advocating for the adoption of community-informed bias evaluation frameworks to more effectively identify and address underrepresented harms in LLMs.

Machine learning models may capture and amplify biases present in data, leading to disparate test performance across social groups. To better understand, evaluate, and mitigate these possible biases, a deeper theoretical understanding of how model design choices and data distribution properties could contribute to bias is needed. In this work, we contribute a precise analytical theory in the context of ridge regression, both with and without random projections, where the former models neural networks in a simplified regime. Our theory offers a unified and rigorous explanation of machine learning bias, providing insights into phenomena such as bias amplification and minority-group bias in various feature and parameter regimes. For example, we demonstrate that there may be an optimal regularization penalty or training time to avoid bias amplification, and there can be fundamental differences in test error between groups that do not vanish with increased parameterization. Importantly, our theoretical predictions align with several empirical observations reported in the literature.

Graph neural network (GNN) link prediction is increasingly deployed in citation, collaboration, and online social networks to recommend academic literature, collaborators, and friends. While prior research has investigated the dyadic fairness of GNN link prediction, the within-group fairness and ``rich get richer'' dynamics of link prediction remain underexplored. However, these aspects have significant consequences for degree and power imbalances in networks. In this paper, we shed light on how degree bias in networks affects Graph Convolutional Network (GCN) link prediction. In particular, we theoretically uncover that GCNs with a symmetric normalized graph filter have a within-group preferential attachment bias. We validate our theoretical analysis on real-world citation, collaboration, and online social networks. We further bridge GCN's preferential attachment bias with unfairness in link prediction and propose a new within-group fairness metric. This metric quantifies disparities in link prediction scores between social groups, towards combating the amplification of degree and power disparities. Finally, we propose a simple training-time strategy to alleviate within-group unfairness, and we show that it is effective on citation, online social, and credit networks.

The expressive power of graph neural networks is usually measured by comparing how many pairs of graphs or nodes an architecture can possibly distinguish as non-isomorphic to those distinguishable by the $k$-dimensional Weisfeiler-Lehman ($k$-WL) test. In this paper, we uncover misalignments between graph machine learning practitioners' conceptualizations of expressive power and $k$-WL through a systematic analysis of the reliability and validity of $k$-WL. We conduct a survey ($n = 18$) of practitioners to surface their conceptualizations of expressive power and their assumptions about $k$-WL. In contrast to practitioners' opinions, our analysis (which draws from graph theory and benchmark auditing) reveals that $k$-WL does not guarantee isometry, can be irrelevant to real-world graph tasks, and may not promote generalization or trustworthiness. We argue for extensional definitions and measurement of expressive power based on benchmarks. We further contribute guiding questions for constructing such benchmarks, which is critical for graph machine learning practitioners to develop and transparently communicate our understandings of expressive power.

Which parts of a dataset will a given model find difficult? Recent work has shown that SGD-trained models have a bias towards simplicity, leading them to prioritize learning a majority class, or to rely upon harmful spurious correlations. Here, we show that the preference for "easy" runs far deeper: A model may prioritize any class or group of the dataset that it finds simple-at the expense of what it finds complex-as measured by performance difference on the test set. When subsets with different levels of complexity align with demographic groups, we term this difficulty disparity, a phenomenon that occurs even with balanced datasets that lack group/label associations. We show how difficulty disparity is a model-dependent quantity, and is further amplified in commonly-used models as selected by typical average performance scores. We quantify an amplification factor across a range of settings in order to compare disparity of different models on a fixed dataset. Finally, we present two real-world examples of difficulty amplification in action, resulting in worse-than-expected performance disparities between groups even when using a balanced dataset. The existence of such disparities in balanced datasets demonstrates that merely balancing sample sizes of groups is not sufficient to ensure unbiased performance. We hope this work presents a step towards measurable understanding of the role of model bias as it interacts with the structure of data, and call for additional model-dependent mitigation methods to be deployed alongside dataset audits.

Discriminative self-supervised learning allows training models on any random group of internet images, and possibly recover salient information that helps differentiate between the images. Applied to ImageNet, this leads to object centric features that perform on par with supervised features on most object-centric downstream tasks. In this work, we question if using this ability, we can learn any salient and more representative information present in diverse unbounded set of images from across the globe. To do so, we train models on billions of random images without any data pre-processing or prior assumptions about what we want the model to learn. We scale our model size to dense 10 billion parameters to avoid underfitting on a large data size. We extensively study and validate our model performance on over 50 benchmarks including fairness, robustness to distribution shift, geographical diversity, fine grained recognition, image copy detection and many image classification datasets. The resulting model, not only captures well semantic information, it also captures information about artistic style and learns salient information such as geolocations and multilingual word embeddings based on visual content only. More importantly, we discover that such model is more robust, more fair, less harmful and less biased than supervised models or models trained on object centric datasets such as ImageNet.

Convolutional architectures have proven extremely successful for vision tasks. Their hard inductive biases enable sample-efficient learning, but come at the cost of a potentially lower performance ceiling. Vision Transformers (ViTs) rely on more flexible self-attention layers, and have recently outperformed CNNs for image classification. However, they require costly pre-training on large external datasets or distillation from pre-trained convolutional networks. In this paper, we ask the following question: is it possible to combine the strengths of these two architectures while avoiding their respective limitations? To this end, we introduce gated positional self-attention (GPSA), a form of positional self-attention which can be equipped with a "soft" convolutional inductive bias. We initialize the GPSA layers to mimic the locality of convolutional layers, then give each attention head the freedom to escape locality by adjusting a gating parameter regulating the attention paid to position versus content information. The resulting convolutional-like ViT architecture, ConViT, outperforms the DeiT on ImageNet, while offering a much improved sample efficiency. We further investigate the role of locality in learning by first quantifying how it is encouraged in vanilla self-attention layers, then analyzing how it is escaped in GPSA layers. We conclude by presenting various ablations to better understand the success of the ConViT. Our code and models are released publicly.