面向过离散潜变量建模的负二项变分自编码器
Negative Binomial Variational Autoencoders for Overdispersed Latent Modeling
为VAE类生成模型提供了一种带离散计数潜变量的替代方案：用负二项分布刻画过离散的脉冲式潜变量，并给出可用的KL估计与重参数化技巧，可直接替换Poisson VAE的等均值-方差假设，用于需要稀疏、离散潜表征的视觉重建与生成任务。
原文依据 we propose NegBio-VAE, a negative-binomial latent-variable model with a dispersion parameter for flexible spike count modeling
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论尽管人工神经网络常被描述为受大脑启发，但其表征通常依赖连续激活，例如变分自编码器（VAE）中的连续潜变量，这与真实神经元中基于脉冲的离散信号相比，限制了其生物合理性。诸如泊松VAE之类的扩展引入了基于计数的离散潜变量，但其均值-方差相等的假设无法刻画神经脉冲中的过离散现象，导致表征的表达能力和信息量下降。为解决这一问题，我们提出NegBio-VAE，一种带有离散度参数的负二项潜变量模型，可灵活地对脉冲计数建模。NegBio-VAE通过新颖的KL估计与重参数化，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取得更优结果，并为下游任务产生鲁棒且信息丰富的潜表征。我们进行了大量消融实验，以验证模型相对于各组成部分的鲁棒性。
英文原文摘要 1147 字符
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, 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.