More Like this

1. Examining the Contribution of Physical Cues for Same- and Cross-Race Face Individuation

   https://doi.org/10.1177/01461672221141510  

   Correll, Joshua; Ma, Debbie_S; Kenny, David_A; Palma, Tomás_A (January 2023, Personality and Social Psychology Bulletin)

   Face individuation involves sensitivity to physical characteristics that provide information about identity. We examined whether Black and White American faces differ in terms of individuating information, and whether Black and White perceivers differentially weight information when judging same-race and cross-race faces. Study 1 analyzed 20 structural metrics (e.g., eye width, nose length) of 158 Black and White faces to determine which differentiate faces within each group. High-utility metrics (e.g., nose length, eye height, chin length) differentiated faces of both groups, low-utility metrics (e.g., face width, eye width, face length) offered less individuating information. Study 2 ( N = 4,510) explored Black and White participants’ sensitivity to variation on structural metrics using similarity ratings. High-utility metrics affected perceived dissimilarity more than low-utility metrics. This relationship was non-significantly stronger for same-race faces rather than cross-race faces. Perceivers also relied more on features that were racially stereotypic of the faces they were rating. 

   more » « less
2. Density zoning, neighborhood type, and exclusion by income and race

   Durst, Noah J; Breshears, Elise; Sullivan, Esther; Gutierrez_Lanza, Danna (June 2025, Journal of housing economics)

   In recent years, states and municipalities have taken steps to reform land use and zoning regulations. While prior research documents that density zoning contributes to residential segregation on the basis of income and race, the mechanisms remain largely unexplored. In this paper, we examine the relationship between density zoning, neighborhood type, and residential segregation. To do so, we use a national dataset of building footprints and machine learning to develop a neighborhood typology based on building characteristics. We then use land cover data to examine changes in building development in these neighborhoods between 2001 and 2019. Finally, we pair these data with demographics at the municipality level to examine changes in income and race between 2000 and 2020. In cross-sectional analyses, we find that density zoning is strongly associated with building characteristics and the presence of different neighborhood types. Although we find that density zoning is also associated with income and race, the effects are attenuated when accounting for neighborhood types. Our results provide new evidence into the ``chain of exclusion" between density zoning and residential segregation, as we find that density zoning is primarily associated with reductions in the supply of single-family housing along the urban fringe. Lastly, we find that maximum density restrictions and changes in maximum density cannot explain the changes in demographics that we observe during this time period. We do, however, find some evidence of a relationship between changes in building development and changes in demographics. These results demonstrate the potential effects of upzoning policies. 

   more » « less
3. Cross-Modality Protein Embedding for Compound-Protein Affinity and Contact Prediction

   You, Yuning; Shen, Yang (December 2020, Machine Learning for Structure Biology (MLSB) Workshop at the 34th Conference on Neural Information Processing Systems)

   null (Ed.)

   Compound-protein pairs dominate FDA-approved drug-target pairs and the prediction of compound-protein affinity and contact (CPAC) could help accelerate drug discovery. In this study we consider proteins as multi-modal data including 1D amino-acid sequences and (sequence-predicted) 2D residue-pair contact maps. We empirically evaluate the embeddings of the two single modalities in their accuracyand generalizability of CPAC prediction (i.e. structure-free interpretable compound-protein affinity prediction). And we rationalize their performances in both challenges of embedding individual modalities and learning generalizable embedding-label relationship. We further propose two models involving cross-modality protein embedding and establish that the one with cross interaction (thus capturing correlations among modalities) outperforms SOTAs and our single modality models in affinity, contact, and binding-site predictions for proteins never seen in the training set. 

   more » « less
4. Within-person dynamics of attention to race and expression of race bias: a real-time test of the self-regulation of prejudice model

   https://doi.org/10.1093/scan/nsaf026  

   Brancaleone, Paul_J; Cofresí, Roberto_U; Volpert-Esmond, Hannah_I; Amodio, David_M; Ito, Tiffany_A; Bartholow, Bruce_D (March 2025, Social Cognitive and Affective Neuroscience)

   Abstract Prior research has supported some aspects of a theorized prejudice self-regulation model. We provide the first test of the full model-based process of bias regulation as it unfolds in real time. Event-related potentials (ERPs) were recorded from White undergraduates at two large American universities (N = 130; 40% female) during a racial stereotype priming task. Attention to Black male face primes, indexed by the P2 ERP, increased following self-regulation failures. In turn, within-person, trial-to-trial variability in attention to Black male faces predicted variability in bias expression. The latter effect was moderated by individual differences in internal motivation to respond without prejudice (IMS). Specifically, among lower-IMS individuals, trials in which Black faces elicited relatively larger P2 amplitudes (relative to an individual’s own average P2 amplitude) were associated with increased behavioral race bias. In contrast, and consistent with theory, among higher-IMS individuals trials in which Black faces elicited larger relative P2 amplitudes were associated with decreased bias. Findings provide direct evidence supporting the temporal sequencing of race-bias regulation and identify within-person variability in attention to race as a potential mechanism for determining when and in whom bias will be regulated. 

   more » « less
5. Inclusive Portraits: Race-Aware Human-in-the-Loop Technology

   https://doi.org/10.1145/3617694.3623235  

   Flores-Saviaga, Claudia; Curtis, Christopher; Savage, Saiph (October 2023, ACM)

   AI has revolutionized the processing of various services, including the automatic facial verification of people. Automated approaches have demonstrated their speed and efficiency in verifying a large volume of faces, but they can face challenges when processing content from certain communities, including communities of people of color. This challenge has prompted the adoption of "human-inthe-loop" (HITL) approaches, where human workers collaborate with the AI to minimize errors. However, most HITL approaches do not consider workers’ individual characteristics and backgrounds. This paper proposes a new approach, called Inclusive Portraits (IP), that connects with social theories around race to design a racially-aware human-in-the-loop system. Our experiments have provided evidence that incorporating race into human-in-the-loop (HITL) systems for facial verification can significantly enhance performance, especially for services delivered to people of color. Our findings also highlight the importance of considering individual worker characteristics in the design of HITL systems, rather than treating workers as a homogenous group. Our research has significant design implications for developing AI-enhanced services that are more inclusive and equitable. 

   more » « less