Benchmarking Fairness in Spiking Neural Networks: Data Bias, Spurious Features, and Hardware Effects

• URL: http://arxiv.org/abs/2605.27407v1
• Date: Fri, 08 May 2026 02:29:00 GMT
• Title: Benchmarking Fairness in Spiking Neural Networks: Data Bias, Spurious Features, and Hardware Effects
• Abstract summary: This work introduces the first systematic fairness benchmark for Spiking Neural Networks (SNNs)<n>Standardized evaluations of 12 state-of-the-art SNNs reveal stark disparities.<n>By bridging algorithmic fairness research with neuromorphic engineering, our benchmark provides a foundation for trustworthy SNNs.
• Score: 11.357028414303842
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Evaluating fairness in Spiking Neural Networks (SNNs) demands rigorous benchmarks that reflect real-world complexities, yet existing assessments remain limited by superficial dataset diversity and idealized hardware assumptions. This work introduces the first systematic fairness benchmark for SNNs, addressing three critical dimensions of realism: (1) demographic coverage gaps in training data, (2) spurious feature leakage (e.g., skin tone as a proxy for class labels), and (3) deployment-environment mismatches (e.g., edge devices with constrained spike encoding). Our framework integrates four cross-demographic datasets with controlled bias injections and three neuromorphic hardware simulators (Loihi 2, SpiNNaker), enabling isolated analysis of fairness-performance trade-offs under resource constraints. Standardized evaluations of 12 state-of-the-art SNNs reveal stark disparities: models trained on biased data exhibit 23\% higher false positive rates for underrepresented groups, while hardware limitations (e.g., reduced spike precision) further amplify accuracy gaps by up to 41\% in edge deployments. Critically, bias mitigation strategies developed for cloud-based SNNs often degrade under resource constraints, highlighting the need for co-design principles that jointly optimize fairness and hardware efficiency. By bridging algorithmic fairness research with neuromorphic engineering, our benchmark provides a foundation for trustworthy SNNs in socially critical applications such as healthcare and autonomous systems. Our code is available at: https://anonymous.4open.science/r/SNN-Benchmarks-8017.

Related papers

• Model-Agnostic Fairness Regularization for GNNs with Incomplete Sensitive Information [11.900835813533135]
  Graph Neural Networks (GNNs) have demonstrated exceptional efficacy in relational learning tasks, including node classification and link prediction.<n>GNNs can perpetuate and even amplify societal biases against protected groups defined by sensitive attributes such as race or gender.<n>We propose a novel, model-agnostic fairness regularization framework designed for the realistic scenario where sensitive attributes are only partially available.
  arXiv  Detail & Related papers  (2025-11-27T15:36:16Z)
• S$^2$NN: Sub-bit Spiking Neural Networks [53.08060832135342]
  Spiking Neural Networks (SNNs) offer an energy-efficient paradigm for machine intelligence.<n>Despite recent advances in binary SNNs, the storage and computational demands remain substantial for large-scale networks.<n>We propose Sub-bit Spiking Neural Networks (S$2$NNs) that represent weights with less than one bit.
  arXiv  Detail & Related papers  (2025-09-29T04:17:44Z)
• Exploiting Label Skewness for Spiking Neural Networks in Federated Learning [19.97002315960335]
  FedLEC incorporates intra-client label weight calibration to balance the learning intensity across local labels and inter-client knowledge distillation to mitigate local SNN model bias.<n>Compared to eight state-of-the-art FL algorithms, FedLEC achieves an average accuracy improvement of approximately 11.59% for the global SNN model.
  arXiv  Detail & Related papers  (2024-12-23T05:52:32Z)
• Positional Encoder Graph Quantile Neural Networks for Geographic Data [4.277516034244117]
  We propose a novel framework that combines PE-GNNs with Quantile Neural Networks, partially monotonic neural blocks, and post-hoc recalibration techniques.<n>The PE-GQNN enables flexible and robust conditional density estimation with minimal assumptions about the target distribution, and it extends naturally to tasks beyond spatial data.
  arXiv  Detail & Related papers  (2024-09-27T16:02:12Z)
• Neural Machine Unranking [3.2340528215722553]
  We introduce a novel task termed Neural Machine UnRanking (NuMuR)<n>Existing task- or model- agnostic unlearning approaches are suboptimal for NuMuR due to two core challenges.<n>CoCoL comprises (1) a contrastive loss that reduces relevance scores on forget sets while maintaining performance on entangled samples, and (2) a consistent loss that preserves accuracy on retain set.
  arXiv  Detail & Related papers  (2024-08-09T20:36:40Z)
• Provable Robustness of (Graph) Neural Networks Against Data Poisoning and Backdoor Attacks [50.87615167799367]
  We certify Graph Neural Networks (GNNs) against poisoning attacks, including backdoors, targeting the node features of a given graph.<n>Our framework provides fundamental insights into the role of graph structure and its connectivity on the worst-case behavior of convolution-based and PageRank-based GNNs.
  arXiv  Detail & Related papers  (2024-07-15T16:12:51Z)
• MAPPING: Debiasing Graph Neural Networks for Fair Node Classification with Limited Sensitive Information Leakage [1.5438758943381854]
  We propose a novel model-agnostic debiasing framework named MAPPING for fair node classification.<n>Our results show that MAPPING can achieve better trade-offs between utility and fairness, and privacy risks of sensitive information leakage.
  arXiv  Detail & Related papers  (2024-01-23T14:59:46Z)
• S2-BNN: Bridging the Gap Between Self-Supervised Real and 1-bit Neural Networks via Guided Distribution Calibration [74.5509794733707]
  We present a novel guided learning paradigm from real-valued to distill binary networks on the final prediction distribution. Our proposed method can boost the simple contrastive learning baseline by an absolute gain of 5.515% on BNNs. Our method achieves substantial improvement over the simple contrastive learning baseline, and is even comparable to many mainstream supervised BNN methods.
  arXiv  Detail & Related papers  (2021-02-17T18:59:28Z)
• FATNN: Fast and Accurate Ternary Neural Networks [89.07796377047619]
  Ternary Neural Networks (TNNs) have received much attention due to being potentially orders of magnitude faster in inference, as well as more power efficient, than full-precision counterparts. In this work, we show that, under some mild constraints, computational complexity of the ternary inner product can be reduced by a factor of 2. We elaborately design an implementation-dependent ternary quantization algorithm to mitigate the performance gap.
  arXiv  Detail & Related papers  (2020-08-12T04:26:18Z)
• Fairness Through Robustness: Investigating Robustness Disparity in Deep Learning [61.93730166203915]
  We argue that traditional notions of fairness are not sufficient when the model is vulnerable to adversarial attacks. We show that measuring robustness bias is a challenging task for DNNs and propose two methods to measure this form of bias.
  arXiv  Detail & Related papers  (2020-06-17T22:22:24Z)
• Neural Networks and Value at Risk [59.85784504799224]
  We perform Monte-Carlo simulations of asset returns for Value at Risk threshold estimation. Using equity markets and long term bonds as test assets, we investigate neural networks. We find our networks when fed with substantially less data to perform significantly worse.
  arXiv  Detail & Related papers  (2020-05-04T17:41:59Z)

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.