Learning Chern Numbers of Topological Insulators with Gauge Equivariant Neural Networks
This work applies gauge-equivariant networks to topological condensed matter physics, enabling accurate prediction of Chern numbers with guaranteed invariance, which is an incremental advancement in using equivariant architectures for local symmetry problems.
The authors tackled the problem of predicting topological invariants (Chern numbers) in multiband topological insulators by using gauge-equivariant neural networks, achieving generalization to non-trivial Chern numbers despite training only on trivial samples. They introduced a novel gauge equivariant normalization layer to stabilize training and proved a universal approximation theorem for their setup.
Equivariant network architectures are a well-established tool for predicting invariant or equivariant quantities. However, almost all learning problems considered in this context feature a global symmetry, i.e. each point of the underlying space is transformed with the same group element, as opposed to a local ``gauge'' symmetry, where each point is transformed with a different group element, exponentially enlarging the size of the symmetry group. Gauge equivariant networks have so far mainly been applied to problems in quantum chromodynamics. Here, we introduce a novel application domain for gauge-equivariant networks in the theory of topological condensed matter physics. We use gauge equivariant networks to predict topological invariants (Chern numbers) of multiband topological insulators. The gauge symmetry of the network guarantees that the predicted quantity is a topological invariant. We introduce a novel gauge equivariant normalization layer to stabilize the training and prove a universal approximation theorem for our setup. We train on samples with trivial Chern number only but show that our models generalize to samples with non-trivial Chern number. We provide various ablations of our setup. Our code is available at https://github.com/sitronsea/GENet/tree/main.