Searching for a path between two nodes in a graph is one of the most well-studied and fundamental problems in computer science. In numerous domains such as robotics, AI, or biology, practitioners develop search heuristics to accelerate their pathfinding algorithms. However, it is a laborious and complex process to hand-design heuristics based on the problem and the structure of a given use case. Here we present PHIL (Path Heuristic with Imitation Learning), a novel neural architecture and a training algorithm for discovering graph search and navigation heuristics from data by leveraging recent advances in imitation learning and graph representation learning. At training time, we aggregate datasets of search trajectories and ground-truth shortest path distances, which we use to train a specialized graph neural network-based heuristic function using backpropagation through steps of the pathfinding process. Our heuristic function learns graph embeddings useful for inferring node distances, runs in constant time independent of graph sizes, and can be easily incorporated in an algorithm such as A* at test time. Experiments show that PHIL reduces the number of explored nodes compared to state-of-the-art methods on benchmark datasets by 58.5% on average, can be directly applied in diverse graphs ranging from biological networks to road networks, and allows for fast planning in time-critical robotics domains.

Learning Graph Search Heuristics / Pandy, M.; Qiu, W.; Corso, G.; Velickovic, P.; Ying, R.; Leskovec, J.; Lio, P.. - 198:(2022). (Intervento presentato al convegno 1st Learning on Graphs Conference, LOG 2022 tenutosi a Virtual, Online).

Learning Graph Search Heuristics

Lio P.
2022

Abstract

Searching for a path between two nodes in a graph is one of the most well-studied and fundamental problems in computer science. In numerous domains such as robotics, AI, or biology, practitioners develop search heuristics to accelerate their pathfinding algorithms. However, it is a laborious and complex process to hand-design heuristics based on the problem and the structure of a given use case. Here we present PHIL (Path Heuristic with Imitation Learning), a novel neural architecture and a training algorithm for discovering graph search and navigation heuristics from data by leveraging recent advances in imitation learning and graph representation learning. At training time, we aggregate datasets of search trajectories and ground-truth shortest path distances, which we use to train a specialized graph neural network-based heuristic function using backpropagation through steps of the pathfinding process. Our heuristic function learns graph embeddings useful for inferring node distances, runs in constant time independent of graph sizes, and can be easily incorporated in an algorithm such as A* at test time. Experiments show that PHIL reduces the number of explored nodes compared to state-of-the-art methods on benchmark datasets by 58.5% on average, can be directly applied in diverse graphs ranging from biological networks to road networks, and allows for fast planning in time-critical robotics domains.
2022
1st Learning on Graphs Conference, LOG 2022
Graph neural networks; Graph theory; Learning algorithms; Machine learning; Robot programming
04 Pubblicazione in atti di convegno::04b Atto di convegno in volume
Learning Graph Search Heuristics / Pandy, M.; Qiu, W.; Corso, G.; Velickovic, P.; Ying, R.; Leskovec, J.; Lio, P.. - 198:(2022). (Intervento presentato al convegno 1st Learning on Graphs Conference, LOG 2022 tenutosi a Virtual, Online).
File allegati a questo prodotto
File Dimensione Formato  
Pandy_Learning_2021.pdf

accesso aperto

Note: https://physical-reasoning.github.io/assets/pdf/papers/06.pdf
Tipologia: Documento in Post-print (versione successiva alla peer review e accettata per la pubblicazione)
Licenza: Creative commons
Dimensione 519.82 kB
Formato Adobe PDF
519.82 kB Adobe PDF

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11573/1728006
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 2
  • ???jsp.display-item.citation.isi??? 0
social impact