Joël Mathys
YOU?
Author Swipe
Learn to Jump: Adaptive Random Walks for Long-Range Propagation through Graph Hierarchies Open
Message-passing architectures struggle to sufficiently model long-range dependencies in node and graph prediction tasks. We propose a novel approach exploiting hierarchical graph structures and adaptive random walks to address this challen…
View article: Synthetic Data for Blood Vessel Network Extraction
Synthetic Data for Blood Vessel Network Extraction Open
Blood vessel networks in the brain play a crucial role in stroke research, where understanding their topology is essential for analyzing blood flow dynamics. However, extracting detailed topological vessel network information from microsco…
Beyond Interpolation: Extrapolative Reasoning with Reinforcement Learning and Graph Neural Networks Open
Despite incredible progress, many neural architectures fail to properly generalize beyond their training distribution. As such, learning to reason in a correct and generalizable way is one of the current fundamental challenges in machine l…
GraphFSA: A Finite State Automaton Framework for Algorithmic Learning on Graphs Open
Many graph algorithms can be viewed as sets of rules that are iteratively applied, with the number of iterations dependent on the size and complexity of the input graph. Existing machine learning architectures often struggle to represent t…
GraphFSA: A Finite State Automaton Framework for Algorithmic Learning on Graphs Open
Many graph algorithms can be viewed as sets of rules that are iteratively applied, with the number of iterations dependent on the size and complexity of the input graph. Existing machine learning architectures often struggle to represent t…
CoRe-GD: A Hierarchical Framework for Scalable Graph Visualization with GNNs Open
Graph Visualization, also known as Graph Drawing, aims to find geometric embeddings of graphs that optimize certain criteria. Stress is a widely used metric; stress is minimized when every pair of nodes is positioned at their shortest path…
SURF: A Generalization Benchmark for GNNs Predicting Fluid Dynamics Open
Simulating fluid dynamics is crucial for the design and development process, ranging from simple valves to complex turbomachinery. Accurately solving the underlying physical equations is computationally expensive. Therefore, learning-based…
Flood and Echo Net: Algorithmically Aligned GNNs that Generalize Open
Most Graph Neural Networks follow the standard message-passing framework where, in each step, all nodes simultaneously communicate with each other. We want to challenge this paradigm by aligning the computation more closely to the executio…
SALSA-CLRS: A Sparse and Scalable Benchmark for Algorithmic Reasoning Open
We introduce an extension to the CLRS algorithmic learning benchmark, prioritizing scalability and the utilization of sparse representations. Many algorithms in CLRS require global memory or information exchange, mirrored in its execution …
View article: Traffic4cast at NeurIPS 2022 -- Predict Dynamics along Graph Edges from Sparse Node Data: Whole City Traffic and ETA from Stationary Vehicle Detectors
Traffic4cast at NeurIPS 2022 -- Predict Dynamics along Graph Edges from Sparse Node Data: Whole City Traffic and ETA from Stationary Vehicle Detectors Open
The global trends of urbanization and increased personal mobility force us to rethink the way we live and use urban space. The Traffic4cast competition series tackles this problem in a data-driven way, advancing the latest methods in machi…
Abstract Visual Reasoning Enabled by Language Open
While artificial intelligence (AI) models have achieved human or even superhuman performance in many well-defined applications, they still struggle to show signs of broad and flexible intelligence. The Abstraction and Reasoning Corpus (ARC…
Learning Graph Algorithms With Recurrent Graph Neural Networks Open
Classical graph algorithms work well for combinatorial problems that can be thoroughly formalized and abstracted. Once the algorithm is derived, it generalizes to instances of any size. However, developing an algorithm that handles complex…
Hierarchical Graph Structures for Congestion and ETA Prediction Open
Traffic4cast is an annual competition to predict spatio temporal traffic based on real world data. We propose an approach using Graph Neural Networks that directly works on the road graph topology which was extracted from OpenStreetMap dat…