cs.LGNov 3, 2026

Positional Encoding is All You Need for Scalable Equivariance Constraint Relaxation

Authors: Hagay Michaeli, Haggai Maron, Daniel Soudry

Organizations: Technion – Israel Institute of Technology · NVIDIA

Abstract

Equivariant neural networks incorporate known symmetries of the data, such as permutations, rotations, or translations, directly into their architecture, often improving sample efficiency and generalization. However, strict equivariance can make optimization difficult, for example, when the data only approximately satisfy the assumed symmetry, or when the equivariance constraints induce a challenging loss landscape. Recent studies have shown that relaxing equivariance during training by introducing non-equivariant dense linear layers can ease optimization in such cases and improve the performance of the resulting strictly equivariant model, after removing the relaxation layers at test time. While effective, this approach incurs a significant computational overhead, limiting its applicability in scalable architectures. In this work, we propose a more efficient constraint-relaxation method based on positional encoding (PE). Our framework injects a positional encoding with learnable scale that breaks the model's original symmetry. This positional signal is gradually annealed to zero, recovering the original equivariant model by the end of training. Empirically, we demonstrate significant improvements for translational and rotational equivariant models with only marginal compute and memory overhead.

Figures & tables

Appendix figures & tables29 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Oct 21, 2026

Asymmetry Tunneling Beyond Adaptive Equivariance Relaxation

Equivariant neural networks encode prescribed symmetries as powerful inductive biases, yet real-world data may exhibit symmetry-breaking structure that these priors cannot fully capture. Prior work has largely addressed this challenge through model-side equivariance relaxation, seeking an appropriate level of equivariance for the data. This raises a complementary question: must equivariance relaxation be adaptively controlled? To investigate this question, we introduce a residual path alongside a strictly equivariant model and deliberately restrict their interface to examine the transmission of task-relevant structure. Across five benchmarks, we observe both residual collapse and survival despite these restrictions; we call the latter phenomenon asymmetry tunneling. We further characterize this phenomenon through four complementary diagnostics. Our results suggest that adaptive control of equivariance relaxation is not a prerequisite for capturing potential symmetry-breaking structure.
Jul 23, 2026

Flash EQ-Linear: Accelerating Equivariant Linear Layers via Group-wise Discrete Fourier Transform

Equivariant networks embed geometric symmetries as structural priors through weight sharing, achieving remarkable parameter efficiency across vision tasks. However, this parameter efficiency does not translate into compute efficiency: most existing implementations unroll the structured weights into dense matrices and dispatch them to generic dense kernels, so an equivariant layer costs no fewer MACs than its non-equivariant counterpart. In this paper, we observe that the equivariant linear (EQ-Linear) layer---the most fundamental and frequently used module in modern equivariant architectures---is essentially a circular convolution along the group dimension composed with a linear transform along the channel dimension. Building on this observation, we propose Flash EQ-Linear, an exact acceleration algorithm that reduces the cost to 2(T−1)/T22(T-1)/T^2 of the original dense formulation (TT is the equivariant group size) by combining the Fourier convolution theorem along the group dimension with the conjugate symmetry of the real DFT. To translate these computational savings into wall-clock speedups, we further develop dedicated CUDA kernels for the p4\mathrm{p}4 group. At the operator level, Flash EQ-Linear achieves up to 2.1×2.1\times forward speedup over PyTorch's highly optimized F.linear; at the network level, Flash EQ-ViT achieves up to 1.7×{1.7\times} end-to-end speedup over both equivariant and non-equivariant baselines. As an operator-level acceleration algorithm, Flash EQ-Linear provides plug-and-play acceleration for diverse pretrained equivariant models, including EQ-ViT, EQ-Swin, EQ-VMamba, and EQ-INR, without retraining or architectural changes. Code is available at https://github.com/zhongchenzhao/FlashEQLinear.
Mar 27, 2026

Tunable Soft Equivariance with Guarantees

Equivariance is a fundamental property in computer vision models, yet strict equivariance is rarely satisfied in real-world data, which can limit a model's performance. Controlling the degree of equivariance is therefore desirable. We propose a general framework for constructing soft equivariant models by projecting the model weights into a designed subspace. The method applies to any pre-trained architecture and provides theoretical bounds on the induced equivariance error. Empirically, we demonstrate the effectiveness of our method on multiple pre-trained backbones, including ViT and ResNet, across image classification, semantic segmentation, and human-trajectory prediction tasks. Notably, our approach improves the performance while simultaneously reducing equivariance error on the competitive ImageNet benchmark.