DiffPool is a differentiable graph pooling module that can generate hierarchical representations of graphs and can be combined with various graph neural network architectures in an end-to-end fashion. DiffPool learns a differentiable soft cluster assignment for nodes at each layer of a deep GNN, mapping nodes to a set of clusters, which then form the coarsened input for the next GNN layer.

Description and image from: [Hierarchical Graph Representation Learning with Differentiable Pooling](https://arxiv.org/pdf/1806.08804.pdf)

**Generalizable Node Injection Attack**, or **G-NIA**, is an attack scenario for graph neural networks where the attacker injects malicious nodes rather than modifying original nodes or edges to affect the performance of GNNs. G-NIA generates the discrete edges also by Gumbel-Top-𝑘 following OPTI and captures the coupling effect between network structure and node features by a sophisticated designed model. 

 G-NIA explicitly models the most critical feature propagation via jointly modeling. Specifically, the malicious attributes are adopted to guide the generation of edges, modeling the influence of attributes and edges. G-NIA also adopts a model-based framework, utilizing useful information of attacking during model training, as well as saving computational cost during inference without re-optimization.

G-NIA

Single Node Injection Attack against Graph Neural Networks

DiffPool

Hierarchical Graph Representation Learning with Differentiable Pooling

**Residual Connections** are a type of skip-connection that learn residual functions with reference to the layer inputs, instead of learning unreferenced functions. 

Formally, denoting the desired underlying mapping as $\mathcal{H}({x})$, we let the stacked nonlinear layers fit another mapping of $\mathcal{F}({x}):=\mathcal{H}({x})-{x}$. The original mapping is recast into $\mathcal{F}({x})+{x}$.

The intuition is that it is easier to optimize the residual mapping than to optimize the original, unreferenced mapping. To the extreme, if an identity mapping were optimal, it would be easier to push the residual to zero than to fit an identity mapping by a stack of nonlinear layers.

Source	Hierarchical Graph Representation Learning with Differentiable Pooling
Year	2000
Data Source	CC BY-SA - https://paperswithcode.com