Using symmetry as an inductive bias in deep learning has been proven to be a principled approach for sample-efficient model design. However, the relationship between symmetry and the imperative for equivariance in neural networks is not always obvious. Here, we analyze a key limitation that arises in equivariant functions: their incapacity to break symmetry at the level of individual data samples. In response, we introduce a novel notion of 'relaxed equivariance' that circumvents this limitation. We further demonstrate how to incorporate this relaxation into equivariant multilayer perceptrons (E-MLPs), offering an alternative to the noise-injection method. The relevance of symmetry breaking is then discussed in various application domains: physics, graph representation learning, combinatorial optimization and equivariant decoding.

对称性在深度学习中作为归纳偏置已经被证明是一种高效的模型设计方法。然而，在神经网络中对称性与等变性的关系并不总是显而易见。本研究分析了等变函数中出现的一个关键限制：它们无法针对单个数据样本进行对称性打破。为此，我们引入了一种新的“放松等变性”的概念来规避这一限制。我们进一步展示了如何将这种放松应用于等变多层感知机（E-MLPs），从而提供了一种与注入噪声方法相对的选择。随后，讨论了对称性打破在物理学、图表示学习、组合优化和等变解码等各个应用领域的相关性。

对称破缺与等变神经网络