paper-with-me

홈 › Papers

The Deep Equilibrium Algorithmic Reasoner

2024-02-09 · Dobrik Georgiev, Pietro Liò, Davide Buffelli

Recent work on neural algorithmic reasoning has demonstrated that graph neural networks (GNNs) could learn to execute classical algorithms. Doing so, however, has always used a recurrent architecture, where each iteration of the GNN aligns with an algorithm's iteration. Since an algorithm's solution is often an equilibrium, we conjecture and empirically validate that one can train a network to solve algorithmic problems by directly finding the equilibrium. Note that this does not require matching each GNN iteration with a step of the algorithm.

📄 PDF Abstract BibTeX arXiv:2402.06445

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Deep Equilibrium Algorithmic Reasoning

2024-10-19 · Dobrik Georgiev, JJ Wilson, Davide Buffelli, Pietro Liò

Neural Algorithmic Reasoning (NAR) research has demonstrated that graph neural networks (GNNs) could learn to execute classical algorithms. However, most previous approaches have always used a recurrent architecture, whe…

KNARsack: Teaching Neural Algorithmic Reasoners to Solve Pseudo-Polynomial Problems

2025-09-17 · Stjepan Požgaj, Dobrik Georgiev, Marin Šilić, Petar Veličković arxiv

Neural algorithmic reasoning (NAR) is a growing field that aims to embed algorithmic logic into neural networks by imitating classical algorithms. In this extended abstract, we detail our attempt to build a neural algori…

Neural Algorithmic Reasoners informed Large Language Model for Multi-Agent Path Finding

2025-08-25 · Pu Feng, Size Wang, Yuhong Cao, Junkang Liang 외 arxiv

The development and application of large language models (LLM) have demonstrated that foundational models can be utilized to solve a wide array of tasks. However, their performance in multi-agent path finding (MAPF) task…

Graph Neural Network

Recurrent Aggregators in Neural Algorithmic Reasoning

2024-09-11 · Kaijia Xu, Petar Veličković

Neural algorithmic reasoning (NAR) is an emerging field that seeks to design neural networks that mimic classical algorithmic computations. Today, graph neural networks (GNNs) are widely used in neural algorithmic reason…

Transformers meet Neural Algorithmic Reasoners

2024-06-13 · Wilfried Bounsi, Borja Ibarz, Andrew Dudzik, Jessica B. Hamrick 외

Transformers have revolutionized machine learning with their simple yet effective architecture. Pre-training Transformers on massive text datasets from the Internet has led to unmatched generalization for natural languag…

Graph Neural NetworkLanguage ModelingLanguage ModellingNatural Language Understanding