打破中心偏差：用于基于坐标的神经进化的空间分区专家
Breaking the Central Bias: Spatially Partitioned Experts for Coordinate-Based Neuroevolution
浏览论文内容
中文总结 AI 辅助
针对ES-HyperNEAT在MNIST上的中心偏差问题，提出空间分区专家方法，将输入分区并分配独立进化网络，将平均准确率从21%提升至43%，相对提升106%，并扩展了像素覆盖率。
中文摘要 AI 辅助
可进化基底HyperNEAT（ES-HyperNEAT）是一种受生物启发的间接编码方法，它根据空间坐标确定神经元位置和连接权重。在以MNIST作为诊断基准的测试中，该方法表现出一种失败模式。由于输入像素映射到以原点为中心的空间坐标系，进化出的网络会收敛到一小簇中心输入像素上，这是一种空间集中偏差；先前的研究在该设置下仅观察到21%的平均准确率。这种偏差是优化产物还是架构天花板？受混合专家（MoE）原理的启发，我们将输入划分为不重叠的空间区域，每个区域分配给一个单独进化的专家网络。采用13个这样的专家，该设计达到了43%的平均准确率，相对基线提升了106%。架构增益不依赖于数据驱动的聚合：使用等权平均（不使用验证数据）已经产生了70%的提升；增益来自分区而非加权。感受野分析揭示了其机制：分区迫使进化在整个图像中发现特征，将活跃像素覆盖率从4%扩大到79%。绝对准确率仍低于梯度训练基线，但相对增益指向中心偏差，而非进化搜索本身。我们设计了两种工具以推广到MNIST之外：一种用于检测静默输入覆盖崩溃的感受野诊断工具，以及一种恢复覆盖的空间分区补救措施。
英文摘要
Evolvable-Substrate HyperNEAT (ES-HyperNEAT), a bio-inspired indirect encoding that determines neuron placement and connection weights from spatial coordinates, exhibits a failure mode on MNIST as a diagnostic benchmark. Because input pixels map to a coordinate space centered at the origin, evolved networks converge on a small central cluster of input pixels, a spatial-concentration bias; prior work observed only 21% mean accuracy in this regime. Is this bias an optimization artifact or an architectural ceiling? Inspired by Mixture-of-Experts (MoE) principles, we partition the input into non-overlapping spatial segments, each assigned to a separately evolved specialist network. With 13 such experts, this design reaches 43% mean accuracy, a 106% relative improvement over the baseline. The architectural gain does not depend on data-driven aggregation: equal-weighted averaging, which uses no validation data, already yields a 70% improvement; the gain comes from partitioning, not the weighting. Receptive-field analysis shows the mechanism: partitioning forces evolution to discover features across the entire image, expanding active pixel coverage from 4% to 79%. Absolute accuracy stays below gradient-trained baselines, but the relative gain points to central bias, not the evolutionary search. Two tools are designed to generalize beyond MNIST: a receptive-field diagnostic for silent input-coverage collapse, and a spatial-partitioning remedy that restores coverage.
发表机构
- University of Neuchâtel（纳沙泰尔大学）
- University College Dublin（都柏林大学学院）
机构由 AI 辅助整理，请以论文原文为准。
