改进的拓扑通行调度:SE(3)等变结构预测中动态k近邻图的阻尼信赖域补偿
Refined Topology-Pass Scheduling: Damped Trust-Region Compensation for Dynamic k-NN Graphs in SE(3)-Equivariant Structure Prediction
AI总结:
本文针对SE(3)等变结构预测中的动态kNN图,提出改进的两通行拓扑调度方法,通过阻尼信赖域补偿解决冻结图的拓扑间隙问题,实现训练周期1.76倍提速且无损失。
摘要:
等变结构预测流程交替进行坐标更新与k近邻(kNN)图的构建,该图的成员关系是坐标的离散分段常数函数。在每个块边界(PB)重建该图是一个训练周期中耗时的部分,而复用单个冻结图(F)速度快但会留下拓扑间隙。本文研究一种两通行设计:廉价通行记录少量状态(边距、kNN半径、每边界位移测量值),第二通行进行保守补偿。我们将图构建基的选择表述为阻尼不动点迭代,其唯一不动点恰好为PB,并推导得到:(i)带双边常数$m_i/4$和单边常数$m_i/2$的精确非翻转证书;(ii)最小方差(BLUE)重放增益$γ^*$及由此产生的可行性交叉;(iii)保持收敛的$\boldsymbol{\textit{ℓ}}_\text{∞}$信赖域投影;(iv)解析近等间距定律$E[m] \text{≈} r_k/(3k)$,其与测量值匹配度达1%。三种补偿级别用C++实现(L1:带实时几何的冻结集;L2:边距门控局部修复;L3:阻尼投影基),并在匹配条件协议(相同种子、MSA深度和轨迹族,仅拓扑模式不同)下验证。L2精确重现PB边集(每个边界处$D = 0.0000$),L1误差在0.6%以内,L3单调插值:移除信赖域时L2精确重现PB边集,L3在冻结拓扑与PB拓扑间插值。记录的轨迹使通行1提速1.5倍,训练周期提速1.76倍,且无测量损失。本文运行时及所有实验的开源实现可在https://github.com/AlbertHuang96/ProteinPredictMachineLearning获取。
英文摘要:
Equivariant structure-prediction pipelines alternate coordinate updates with the construction of a k-nearest-neighbour (kNN) graph whose membership is a discrete, piecewise-constant function of the coordinates. Rebuilding that graph at every block boundary (PB) is the expensive part of an epoch, whereas reusing one frozen graph (F) is fast but leaves a topology gap. We study a two-pass design in which the cheap pass records a small amount of state (margins, kNN radii, measured per-boundary displacements) and a second pass compensates conservatively. We formulate the choice of the graph-construction basis as a damped fixed-point iteration whose unique fixed point is exactly PB, and derive (i) exact non-flip certificates with the two-sided constant $m_i/4$ and one-sided constant $m_i/2$, (ii) the minimum-variance (BLUE) replay gain $γ^*$ and the resulting feasibility crossover, (iii) an $\ell_\infty$ trust-region projection that preserves convergence, and (iv) an analytic near-tie spacing law $E[m] \approx r_k/(3k)$ that matches measurements to 1\%. Three compensation levels are implemented in C++ (L1: frozen set with live geometry; L2: margin-gated local repair; L3: damped, projected basis) and validated under a matched-conditions protocol (identical seed, MSA depth and trajectory family, only the topology mode differs). L2 reproduces the PB edge set exactly ($D = 0.0000$ at every boundary), L1 stays within 0.6% and L3 interpolates monotonically: L2 reproduces the PB edge set exactly when the trust region is removed, and L3 interpolates between the frozen and the PB topology. The recorded trajectory itself yields a measured $1.5\times$ Pass-1 and $1.76\times$ epoch speed-up with no measurable loss gap. An open-source implementation of the runtime and of all the experiments reported here is available at https://github.com/AlbertHuang96/ProteinPredictMachineLearning.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。