<ul><li>Equivariant networks encode known symmetries into neural networks, but they are unable to break symmetries.</li><li>Equivariant networks must have at least the same self-symmetries as the input, which limits their ability to handle prediction tasks and generative models.</li><li>To address this limitation, equivariant conditional distributions are considered instead of equivariant functions.</li><li>The SymPE method, which uses symmetry-breaking positional encodings, allows the breaking of symmetries while retaining the inductive bias of symmetry in equivariant networks.</li></ul>

Improving Equivariant Networks with Probabilistic Symmetry Breaking

Discover more