Set Twister for Single-hop Node Classification

12/17/2021
by   Yangze Zhou, et al.
0

Node classification is a central task in relational learning, with the current state-of-the-art hinging on two key principles: (i) predictions are permutation-invariant to the ordering of a node's neighbors, and (ii) predictions are a function of the node's r-hop neighborhood topology and attributes, r ≥ 2. Both graph neural networks and collective inference methods (e.g., belief propagation) rely on information from up to r-hops away. In this work, we study if the use of more powerful permutation-invariant functions can sometimes avoid the need for classifiers to collect information beyond 1-hop. Towards this, we introduce a new architecture, the Set Twister, which generalizes DeepSets (Zaheer et al., 2017), a simple and widely-used permutation-invariant representation. Set Twister theoretically increases expressiveness of DeepSets, allowing it to capture higher-order dependencies, while keeping its simplicity and low computational cost. Empirically, we see accuracy improvements of Set Twister over DeepSets as well as a variety of graph neural networks and collective inference schemes in several tasks, while showcasing its implementation simplicity and computational efficiency.

READ FULL TEXT
research
05/31/2018

HOPF: Higher Order Propagation Framework for Deep Collective Classification

Given a graph wherein every node has certain attributes associated with ...
research
06/06/2021

Graph Belief Propagation Networks

With the wide-spread availability of complex relational data, semi-super...
research
09/25/2019

PINE: Universal Deep Embedding for Graph Nodes via Partial Permutation Invariant Set Functions

Graph node embedding aims at learning a vector representation for all no...
research
02/06/2023

Collective Robustness Certificates: Exploiting Interdependence in Graph Neural Networks

In tasks like node classification, image segmentation, and named-entity ...
research
03/25/2022

SpeqNets: Sparsity-aware Permutation-equivariant Graph Networks

While (message-passing) graph neural networks have clear limitations in ...
research
12/30/2020

Adaptive Graph Diffusion Networks with Hop-wise Attention

Graph Neural Networks (GNNs) have received much attention recent years a...
research
07/12/2019

Learning Functions over Sets via Permutation Adversarial Networks

In this paper, we consider the problem of learning functions over sets, ...

Please sign up or login with your details

Forgot password? Click here to reset