Non-Homophilic Graph Pre-Training and Prompt Learning

Non-Homophilic Graph Pre-Training and Prompt Learning

KDD25

​#paper/⭐#​

目的：对异配图进行prompt

‍

​​

方法

邻居节点的综合嵌入

s v = 1 ∣ V ( S v ) ∣ ∑ u ∈ V ( S v ) h u ⋅ s i m ( h u , h v ) , \mathbf{s}{v}=\frac{1}{|V(S{v})|}\sum_{u\in V(S_{v})}\mathbf{h}{u}\cdot\mathrm{sim}(\mathbf{h}{u},\mathbf{h}_{v}), sv=∣V(Sv)∣1∑u∈V(Sv)hu⋅sim(hu,hv),

在实践中，作者使用了2hop来表示邻域信息

邻域信息映射

p t , v = C o n d N e t ( s v ; ϕ t ) \mathbf{p}{t,v}=\mathrm{CondNet}(s{v};\phi_{t}) pt,v=CondNet(sv;ϕt)，这里，condnet是一层MLP

h ~ t , v = p t , v ⊙ h v , \tilde{\mathbf{h}}{t,v}=\mathbf{p}{t,v}\odot\mathbf{h}_{v}, h~t,v=pt,v⊙hv,

与类prototype做prompt

L d o w n ( ϕ t ) = − ∑ ( x i , y i ) ∈ D t ln ⁡ exp ⁡ ( 1 τ sin ⁡ ( h ~ t , x i , h ˉ t , y i ) ) ∑ c ∈ Y exp ⁡ ( 1 τ sin ⁡ ( h ~ t , x i , h ˉ t , c ) ) \mathcal{L}{\mathrm{down}}(\phi{t})=-\sum_{(x_{i},y_{i})\in\mathcal{D}{t}}\ln\frac{\exp\left(\frac{1}{\tau}\sin(\tilde{\mathbf{h}}{t,x_{i}},\bar{\mathbf{h}}{t,y{i}})\right)}{\sum_{c\in Y}\exp\left(\frac{1}{\tau}\sin(\tilde{\mathbf{h}}{t,x{i}},\bar{\mathbf{h}}_{t,c})\right)} Ldown(ϕt)=−∑(xi,yi)∈Dtln∑c∈Yexp(τ1sin(h~t,xi,hˉt,c))exp(τ1sin(h~t,xi,hˉt,yi))

其中， h t , c h_{t,c} ht,c代表属于类C的平均值。

结果：

​​

‍