一、 论文中定理
1、定义1 —— Multiset
A multiset is a generalized concept of a set that allows multiple instances for its elements. More formally, a multiset is a 2-tulle X = ( S , m ) X=(S,m) X=(S,m) where S S S Is the underlying set of X X X that is formed from its distinct elements, and m : S → N ≥ 1 m: S\rightarrow N_{\ge1} m:S→N≥1 gives the multiplicity of the elements.
2、引理2
Let G 1 G_1 G1 and G 2 G_2 G2 be any two non-isomorphic graphs. If a graph neural network A : G → R d A: G\rightarrow R^d A:G→Rd maps G 1 G_1 G1 and G 2 G_2 G2 to different embeddings, the Weisfeiler-Lehman graph isomorphism test also decides G 1 G_1 G1 and G 2 G_2 G2 are not isomorphic.
3、定理3
Let
A
:
G
→
R
d
A: G \rightarrow R^d
A:G→Rd be a GNN. With a sufficient number of GNN layers. A maps any graphs
G
1
G_1
G1 And
G
2
G_2
G2 that the WL test of isomorphism decides as non-isomorphic, to different embeddings if the following conditions hold:
a) A aggregates and updates node features iteratively with:
h
v
(
k
)
=
ϕ
(
h
v
(
k
−
1
)
,
f
(
{
h
u
(
k
−
1
)
:
u
∈
N
(
v
)
}
)
)
h_v^{(k)}=\phi(h_v^{(k-1)},f(\{ h_u^{(k-1)}:u\in N(v)\}))
hv(k)=ϕ(hv(k−1),f({hu(k−1):u∈N(v)}))
Where the functions
f
f
f, which operates on multisets, and
ϕ
\phi
ϕ are invective.
b). A’s graph-level readout, which operates on the multiset of node features
{
h
v
k
}
\{ h_v^{k}\}
{hvk}, is invective.