Language Embedding Meets Dynamic Graph: A New Exploration for Neural Architecture Representation Learning
By: Haizhao Jing , Haokui Zhang , Zhenhao Shang and more
Potential Business Impact:
Helps computers choose the best parts for speed.
Neural Architecture Representation Learning aims to transform network models into feature representations for predicting network attributes, playing a crucial role in deploying and designing networks for real-world applications. Recently, inspired by the success of transformers, transformer-based models integrated with Graph Neural Networks (GNNs) have achieved significant progress in representation learning. However, current methods still have some limitations. First, existing methods overlook hardware attribute information, which conflicts with the current trend of diversified deep learning hardware and limits the practical applicability of models. Second, current encoding approaches rely on static adjacency matrices to represent topological structures, failing to capture the structural differences between computational nodes, which ultimately compromises encoding effectiveness. In this paper, we introduce LeDG-Former, an innovative framework that addresses these limitations through the synergistic integration of language-based semantic embedding and dynamic graph representation learning. Specifically, inspired by large language models (LLMs), we propose a language embedding framework where both neural architectures and hardware platform specifications are projected into a unified semantic space through tokenization and LLM processing, enabling zero-shot prediction across different hardware platforms for the first time. Then, we propose a dynamic graph-based transformer for modeling neural architectures, resulting in improved neural architecture modeling performance. On the NNLQP benchmark, LeDG-Former surpasses previous methods, establishing a new SOTA while demonstrating the first successful cross-hardware latency prediction capability. Furthermore, our framework achieves superior performance on the cell-structured NAS-Bench-101 and NAS-Bench-201 datasets.
Similar Papers
Research on Personalized Financial Product Recommendation by Integrating Large Language Models and Graph Neural Networks
Information Retrieval
Suggests best money products for you.
Brain Network Classification Based on Graph Contrastive Learning and Graph Transformer
Machine Learning (CS)
Helps doctors understand brain scans better.
Relational Graph Transformer
Machine Learning (CS)
Helps computers learn from connected data better.