用负二项分布建模神经信号过分散，提升生成模型生物合理性
Negative Binomial Variational Autoencoders for Overdispersed Latent Modeling
- 采用负二项分布潜变量，引入可调离散度参数模拟真实神经脉冲
- 在4个数据集上重建与生成性能均优于现有单层VAE基线
- 适合需要生物可解释性、处理稀疏计数数据的研究者使用
尽管人工神经网络常被视作类脑设计，其表示通常依赖连续激活（如变分自编码器中的连续潜变量），相比真实神经元的离散脉冲信号，生物合理性不足。现有扩展如泊松VAE虽引入离散计数潜变量，但其均值等于方差的假设无法捕捉神经脉冲的过分散现象，导致表征表达力不足。为此，我们提出NegBio-VAE，一种具有离散度参数的负二项潜变量模型，实现灵活的脉冲计数建模。该模型通过新颖的KL散度估计与重参数化技术，在保持可解释性的同时提升了表征质量与训练可行性。在四个数据集上的实验表明，NegBio-VAE在重建与生成性能上持续优于对比的单层VAE基线，并为下游任务提供稳健、信息丰富的潜变量表示。大量消融实验验证了各组件对模型鲁棒性的贡献。代码已开源：https://github.com/co234/NegBio-VAE。
原文摘要 · Abstract (English)
Although artificial neural networks are often described as brain-inspired, their representations typically rely on continuous activations, such as the continuous latent variables in variational autoencoders (VAEs), which limits their biological plausibility compared to the discrete spike-based signaling in real neurons. Extensions like the Poisson VAE introduce discrete count-based latents, but their equal mean-variance assumption fails to capture overdispersion in neural spikes, leading to less expressive and informative representations. To address this, we propose NegBio-VAE, a negative-binomial latent-variable model with a dispersion parameter for flexible spike count modeling. NegBio-VAE preserves interpretability while improving representation quality and training feasibility via novel KL estimation and reparameterization. Experiments on four datasets demonstrate that NegBio-VAE consistently achieves superior reconstruction and generation performance compared to competing single-layer VAE baselines, and yields robust, informative latent representations for downstream tasks. Extensive ablation studies are performed to verify the model's robustness w.r.t. various components. Our code is available at https://github.com/co234/NegBio-VAE.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。