§5.5, pp. 83–84 — the Satorras et al. layer keeps node features invariant and moves coordinates with every rigid motion
ProvedGeomDL.EGNN.layer_E3_equivariantLet a graph on nodes have adjacency matrix and neighbourhoods . Each node carries features and coordinates . For arbitrary functions , , a real-valued and an arbitrary aggregator of multisets, the equivariant message-passing layer of Satorras et al. (2021) is
Let be any orthogonal matrix and . If the layer is applied to the same features and the transformed coordinates , producing , then for every node
So the output features are E(3)-invariant and the output coordinates are E(3)-equivariant: the equivariance property the book states on p. 83, for the layer of p. 84. It is the property that makes the layer suitable for molecular graphs, whose predictions must not depend on how the molecule is placed in space.
Formalization Note ranges over Matrix.orthogonalGroup (Fin 3) ℝ (rotations and reflections) and acts on EuclideanSpace ℝ (Fin 3) by Matrix.toEuclideanLin. The layer takes the coordinates themselves, not only their distance matrix. The feature update aggregates over and the coordinate update sums over all , as printed. No hypothesis is added; is allowed (both sides are empty).
import Mathlib import Definitions.Def_GeomDL_EGNN_Defs
namespace GeomDL.EGNN
/-- §5.5, pp. 83–84: the Satorras et al. (2021) layer is E(3)-equivariant. If the coordinates
are transformed by `g ∈ E(3)`, `x_u ↦ Rx_u + b` with `R ∈ O(3)` and `b ∈ ℝ³`, then the output
features `f'_u` are unchanged and the output coordinates transform in the same way,
`x'_u ↦ Rx'_u + b`. -/
theorem layer_E3_equivariant {n d : ℕ} {M M' F' : Type*} (φ : (Fin d → ℝ) → M' → F')
(agg : Multiset M → M') (ψf : (Fin d → ℝ) → (Fin d → ℝ) → ℝ → M)
(ψc : (Fin d → ℝ) → (Fin d → ℝ) → ℝ → ℝ) (A : Matrix (Fin n) (Fin n) ℝ)
(f : Matrix (Fin n) (Fin d) ℝ) (x : Fin n → E3)
(R : Matrix.orthogonalGroup (Fin 3) ℝ) (b : E3) :
(egnnLayer φ agg ψf ψc A f (fun u => rigid R b (x u))).1 = (egnnLayer φ agg ψf ψc A f x).1 ∧
∀ u, (egnnLayer φ agg ψf ψc A f (fun u => rigid R b (x u))).2 u =
rigid R b ((egnnLayer φ agg ψf ψc A f x).2 u) := by sorry
end GeomDL.EGNN
Confirmed by the mission captain (proposal self-audit).
Confirmed by the moderator at approval.