← Search

Berke Kisin

2 accepted papers

2024

Distinguished In Uniform: Self-Attention Vs. Virtual Nodes

ICLR 2024poster

Graph Transformers (GTs) such as SAN and GPS are graph processing models that combine Message-Passing GNNs (MPGNNs) with global Self-Attention. They were shown to be universal function approximators, with two reservations: 1. The initial node features must be augmented with certain positional encodi…

2023

One Model, Any CSP: Graph Neural Networks as Fast Global Search Heuristics for Constraint Satisfaction

IJCAI 2023poster

We propose a universal Graph Neural Network architecture which can be trained as an end-2-end search heuristic for any Constraint Satisfaction Problem (CSP). Our architecture can be trained unsupervised with policy gradient descent to generate problem specific heuristics for any CSP in a purely data…