Stronger together? The homophily trap in networks

• URL: http://arxiv.org/abs/2412.20158v1
• Date: Sat, 28 Dec 2024 14:14:16 GMT
• Title: Stronger together? The homophily trap in networks
• Authors: Marcos Oliveira, Leonie Neuhauser, Fariba Karimi,
• Abstract summary: Homophily -- the tendency to link with similar others -- can hinder diversity and widen inequalities.<n>We show that homophily traps arise when minority size falls below 25% of a network.<n>Our work reveals that social groups require a critical size to benefit from homophily without incurring structural costs.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While homophily -- the tendency to link with similar others -- may nurture a sense of belonging and shared values, it can also hinder diversity and widen inequalities. Here, we unravel this trade-off analytically, revealing homophily traps for minority groups: scenarios where increased homophilic interaction among minorities negatively affects their structural opportunities within a network. We demonstrate that homophily traps arise when minority size falls below 25% of a network, at which point homophily comes at the expense of lower structural visibility for the minority group. Our work reveals that social groups require a critical size to benefit from homophily without incurring structural costs, providing insights into core processes underlying the emergence of group inequality in networks.

Related papers

• Homophily Within and Across Groups [0.0]
  We present an exponential family model that integrates both local and global homophily. We show how higher-order assortative mixing influences network dynamics.
  arXiv  Detail & Related papers  (2024-12-10T20:17:04Z)
• How does promoting the minority fraction affect generalization? A theoretical study of the one-hidden-layer neural network on group imbalance [64.1656365676171]
  Group imbalance has been a known problem in empirical risk minimization. This paper quantifies the impact of individual groups on the sample complexity, the convergence rate, and the average and group-level testing performance.
  arXiv  Detail & Related papers  (2024-03-12T04:38:05Z)
• Generalizable Heterogeneous Federated Cross-Correlation and Instance Similarity Learning [60.058083574671834]
  This paper presents a novel FCCL+, federated correlation and similarity learning with non-target distillation. For heterogeneous issue, we leverage irrelevant unlabeled public data for communication. For catastrophic forgetting in local updating stage, FCCL+ introduces Federated Non Target Distillation.
  arXiv  Detail & Related papers  (2023-09-28T09:32:27Z)
• Demystifying Structural Disparity in Graph Neural Networks: Can One Size Fit All? [61.35457647107439]
  Most real-world homophilic and heterophilic graphs are comprised of a mixture of nodes in both homophilic and heterophilic structural patterns. We provide evidence that Graph Neural Networks(GNNs) on node classification typically perform admirably on homophilic nodes. We then propose a rigorous, non-i.i.d PAC-Bayesian generalization bound for GNNs, revealing reasons for the performance disparity.
  arXiv  Detail & Related papers  (2023-06-02T07:46:20Z)
• Group fairness without demographics using social networks [29.073125057536014]
  Group fairness is a popular approach to prevent unfavorable treatment of individuals based on sensitive attributes such as race, gender, and disability. We propose a "group-free" measure of fairness that does not rely on sensitive attributes and, instead, is based on homophily in social networks.
  arXiv  Detail & Related papers  (2023-05-19T00:45:55Z)
• Structural Group Unfairness: Measurement and Mitigation by means of the Effective Resistance [6.7454940931279666]
  Social networks contribute to the distribution of social capital, defined as the relationships, norms of trust and reciprocity within a community. There is a lack of methods to quantify social capital at a group level, which is particularly important when the groups are defined on the grounds of protected attributes. We introduce three effective resistance-based measures of group social capital, namely group isolation, group diameter and group control, where the groups are defined according to the value of a protected attribute.
  arXiv  Detail & Related papers  (2023-05-05T00:57:55Z)
• The Double-Edged Sword of Implicit Bias: Generalization vs. Robustness in ReLU Networks [64.12052498909105]
  We study the implications of the implicit bias of gradient flow on generalization and adversarial robustness in ReLU networks. In two-layer ReLU networks gradient flow is biased towards solutions that generalize well, but are highly vulnerable to adversarial examples.
  arXiv  Detail & Related papers  (2023-03-02T18:14:35Z)
• Semantic-aware Node Synthesis for Imbalanced Heterogeneous Information Networks [51.55932524129814]
  We present the first method for the semantic imbalance problem in imbalanced HINs named Semantic-aware Node Synthesis (SNS) SNS adaptively selects the heterogeneous neighbor nodes and augments the network with synthetic nodes while preserving the minority semantics. We also introduce two regularization approaches for HGNNs that constrain the representation of synthetic nodes from both semantic and class perspectives.
  arXiv  Detail & Related papers  (2023-02-27T00:21:43Z)
• On Graph Neural Network Fairness in the Presence of Heterophilous Neighborhoods [12.531373572440787]
  We study the task of node classification for graph neural networks (GNNs) We establish a connection between group fairness, as measured by statistical parity and equal opportunity, and local assortativity. We show that by adopting heterophilous GNN designs, group fairness in locally heterophilous neighborhoods can be improved by up to 25% over homophilous designs in real and synthetic datasets.
  arXiv  Detail & Related papers  (2022-07-10T04:02:20Z)
• Group mixing drives inequality in face-to-face gatherings [2.7728956081909346]
  We show that the way social groups interact in face-to-face situations can enable the emergence of disparities in the visibility of social groups. We present a mechanism that explains these disparities as the result of group mixing and group-size imbalance.
  arXiv  Detail & Related papers  (2021-06-22T11:44:02Z)
• Contrastive Examples for Addressing the Tyranny of the Majority [83.93825214500131]
  We propose to create a balanced training dataset, consisting of the original dataset plus new data points in which the group memberships are intervened. We show that current generative adversarial networks are a powerful tool for learning these data points, called contrastive examples.
  arXiv  Detail & Related papers  (2020-04-14T14:06:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.