paper-with-me

Papers

X-RLflow: Graph Reinforcement Learning for Neural Network Subgraphs Transformation

2023-04-28 · Guoliang He, Sean Parker, Eiko Yoneki

Tensor graph superoptimisation systems perform a sequence of subgraph substitution to neural networks, to find the optimal computation graph structure. Such a graph transformation process naturally falls into the framework of sequential decision-making, and existing systems typically employ a greedy search approach, which cannot explore the whole search space as it cannot tolerate a temporary loss of performance. In this paper, we address the tensor graph superoptimisation problem by exploring an alternative search approach, reinforcement learning (RL). Our proposed approach, X-RLflow, can learn to perform neural network dataflow graph rewriting, which substitutes a subgraph one at a time. X-RLflow is based on a model-free RL agent that uses a graph neural network (GNN) to encode the target computation graph and outputs a transformed computation graph iteratively. We show that our approach can outperform state-of-the-art superoptimisation systems over a range of deep learning models and achieve by up to 40% on those that are based on transformer-style architectures.

📄 PDF Abstract BibTeX arXiv:2304.14698

Code (1)

ucamrl/xrlflow 공식 구현

Tasks

Decision MakingGraph Neural Networkreinforcement-learningReinforcement LearningReinforcement Learning (RL)Sequential Decision Making

Methods 이 논문이 사용한 방법론

Graph Neural Network 설명 없음

Similar Papers 제목 키워드 기반

RLFlow: Optimising Neural Network Subgraph Transformation with World Models

2022-05-03 · Sean Parker, Sami Alabed, Eiko Yoneki

Training deep learning models takes an extremely long execution time and consumes large amounts of computing resources. At the same time, recent research proposed systems and compilers that are expected to decrease deep …

Deep LearningModel-based Reinforcement Learningreinforcement-learningReinforcement Learning (RL)

Controllable Flow Matching for Online Reinforcement Learning

2025-11-10 · Bin Wang, Boxiang Tao, Haifeng Jing, Hongbo Dou 외 arxiv

Model-based reinforcement learning (MBRL) typically relies on modeling environment dynamics for data efficiency. However, due to the accumulation of model errors over long-horizon rollouts, such methods often face challe…

Reinforcement Learning

5* Knowledge Graph Embeddings with Projective Transformations

2020-06-08 · Mojtaba Nayyeri, Sahar Vahdati, Can Aykul, Jens Lehmann

Performing link prediction using knowledge graph embedding models has become a popular approach for knowledge graph completion. Such models employ a transformation function that maps nodes via edges into a vector space i…

Graph EmbeddingKnowledge Graph CompletionKnowledge Graph EmbeddingKnowledge Graph Embeddings+3

ReGAE: Graph autoencoder based on recursive neural networks

2022-01-28 · Adam Małkowski, Jakub Grzechociński, Paweł Wawrzyński

Invertible transformation of large graphs into fixed dimensional vectors (embeddings) remains a challenge. Its overcoming would reduce any operation on graphs to an operation in a vector space. However, most existing met…

Decoder

MAG-GNN: Reinforcement Learning Boosted Graph Neural Network

2023-10-29 · NeurIPS 2023 11

While Graph Neural Networks (GNNs) recently became powerful tools in graph learning tasks, considerable efforts have been spent on improving GNNs' structural encoding ability. A particular line of work proposed subgraph …

Combinatorial OptimizationGraph LearningGraph Neural Networkreinforcement-learning+2