Geometric Mean Pooling for Equal-Weight Multiplicative Coarse-Graining
Authors: Ang-Kun Wu, Fangdi Wen, Jingtao Zhang
Organizations: Department of Physics and Astronomy, University of Tennessee, Knoxville Knoxville, Tennessee 37996, USA · Department of Physics and Astronomy, Rutgers University New Brunswick, New Jersey 08901, USA · Google Mountain View, CA 94043, USA
As an alternative to the additive and extremal biases of average and max pooling, we introduce Geometric Mean Pooling (GMP), a signed pooling operator that combines the product of feature signs with the geometric mean of feature magnitudes. Motivated by local-to-global composition in quantum many-body physics, GMP retains both joint sign information and a characteristic multiplicative scale without introducing learnable pooling parameters. We show that non-overlapping hierarchical GMP preserves the corresponding global multiplicative statistic and evaluate it on synthetic sequence tasks, iterative coarse-graining, image classification, and molecular lipophilicity regression. On the synthetic tasks, GMP recovers product-based signals more accurately than average and max pooling and maintains predictive performance under the tested levels of multiplicative input noise. On image and molecular data, however, its effectiveness depends on the representation, target parameterization, and placement of local and global pooling. These results position GMP as a complementary, regime-dependent inductive bias for tasks in which equal-weight multiplicative composition is plausible, rather than as a universal replacement for standard pooling operators.
Figures & tables
Figure 1: Sequence-length and cell-size sweeps for Case B classification (top) and R2 regression (bottom). Left: varying sequence length with cell size 3 . Right: varying cell size with sequence length 120 . Clean classification inputs are standard Gaussian; clean regression inputs are lognormal with standard Gaussian logarithms. Targets are computed before adding Gaussian input noise with standard deviation 0.05 . Error bars denote the standard deviation across ten random seeds.
Setting
Accuracy
Case A, signed
0.9330 ± 0.0659
Case A, unsigned
0.5107 ± 0.0165
Case B, signed
0.9856 ± 0.0047
Case B, unsigned
0.5072 ± 0.0136
Table 1: Ablation of the sign-parity term in geometric mean pooling. Results are reported as mean ± standard deviation across 10 random seeds. The sequence length is 120 , and the cell size is 3 for Case B.
Figure 2: R3: global regression under multiplicative and additive input noise, x~=xexp(ϵmul)+ϵadd , with logx∼N(0,1) and independent Gaussian perturbations of standard deviations σmul and σadd . Over the tested noise ranges, GMP maintains higher predictive performance than max pooling, including at low noise levels.
Figure 3: R4: preservation of a multiplicative observable across pooling levels. MAE is evaluated against the clean geometric-mean target ( σ=1 , p=25% , L=256 ), using a global geometric readout after each local pooling step for all methods. GMP maintains an approximately constant readout error across the hierarchy.
Figure 4: Validation accuracy on MNIST, Fashion-MNIST, and CIFAR-10 across ten random seeds. Each panel reports the three pooling primitives (GMP, max, and average) under three architectures: variable global pooling with fixed intermediate max pooling, variable local pooling with fixed global max pooling, and synchronized local-plus-global pooling. Local GMP is generally more competitive than global GMP on MNIST and Fashion-MNIST, whereas the gap between GMP and the gap between GMP and the average- and max-pooling baselines increases on CIFAR-10. Error bars denote standard deviation across 10 seeds. All models are trained with cross-entropy loss and Adam [ 23 ] using batch size 128 and learning rate 10−3 .
Baseline
RMSE
R2
Morgan FP + XGBoost
0.8870
0.4631
Morgan FP + Random Forest
0.8718
0.4813
Morgan FP + FC
0.8752
0.4773
SMILES Embedding + FC
1.1596
0.0824
Table 2: Lipophilicity regression performance on the original logarithmic label scale, using a scaffold split.
Figure 5: Test R2 on the auxiliary target z=exp(y) for the Morgan-fingerprint 2D CNN under all combinations of local and global pooling operators. Each molecule is represented by a radius-2, 2,048-bit Morgan fingerprint, projected to a learned 32×32 latent feature map, and processed by a three-block convolutional hierarchy. Values and error bars denote the mean and standard deviation over ten random seeds.
Appendix figures & tables3 assets
Supplementary material from the paper’s appendix.
Appendix
Sweep
Value
Max acc
Average acc
GMP acc
ρ -sweep (seed=42, seq_len=32)
0.0
0.4680
0.5390
1.0000
0.3
0.5080
0.4860
1.0000
0.5
0.5000
0.4900
1.0000
0.7
0.5130
0.4830
1.0000
0.9
0.6040
0.6040
1.0000
Seq_len sweep (seed=42, ρ=0 )
16
0.5190
0.5190
1.0000
Appendix
Table 3: Case A classification accuracy with seed 42 . The correlation sweep fixes N=32 ; the sequence-length sweep uses independent inputs ( ρ=0 ).
N
R2
MSE ( ×10−3 )
Max
Avg
GMP
Max
Avg
GMP
16
0.137
0.609
1.000
60.7
27.5
0.0
32
0.081
0.620
1.000
29.3
12.1
0.0
64
0.071
0.631
0.993
14.6
5.8
0.0
128
0.019
0.638
1.000
7.9
2.9
0.0
Appendix
Table 4: R1 global geometric-mean regression on noiseless lognormal inputs with seed 42 . Results are reported as R2 and MSE; MSE values are scaled by 103 .
Figure 6: Test R2 for lipophilicity regression on the original label scale using CNNs with different combinations of local and global pooling. Error bars denote the standard deviation across ten random seeds. Max pooling achieves the highest R2 in this setting.