Text-guided molecule generation enables controlled molecular design from natural language descriptions and has broad applications in areas such as drug discovery. While recent methods have demonstrated promising capability in generating molecules that align well with textual descriptions, they often overlook the structural properties of the generated graphs. As a result, these approaches struggle to simultaneously ensure consistency with the input text and high structural quality of the generated molecules. In this paper, we propose a text-guided molecular graph generation framework that leverages the structural modeling power of graph diffusion models to achieve both strong alignment with textual descriptions and high-quality molecular structures. However, accomplishing this goal involves several key challenges: 1) how to align graph diffusion models with natural language instructions in order to generate molecular graphs with expected relational semantics from text, 2) how to directly optimize the quality of the generated molecular graphs without sacrificing fine-grained alignment with text-specific details. To tackle these challenges, we introduce Text-guided Conditional Discrete Graph Diffusion (TDGD), a discrete diffusion-based framework for generating molecular graphs from natural language descriptions. Our model incorporates a structure-aware cross-attention mechanism that aligns textual semantics with molecular structures by capturing relational semantics between textual descriptions and molecular structures. In addition, we propose a molecule structure consistency loss that explicitly enforces structural coherence during generation, leading to higher-quality and more consistent molecular graphs. Extensive experiments on ChEBI-20 and L+M-24 datasets demonstrate the effectiveness of our proposed TDGD model.
Yang Yao, Xin Wang, Yaofei Wu et al.· Proceedings of the 32nd ACM...· 0 citations
Discovering optimal graph neural network (GNN) architectures for various tasks is both labor-intensive and time-consuming. To reduce human effort, graph neural architecture search (GNAS) has recently been utilized to automatically identify effective GNN architectures for specific tasks, achieving competitive or even superior performance compared to manually designed architectures. However, existing GNAS methods fail to identify optimal architectures in the presence of structural and semantic noise, where structural noise refers to missing or redundant edges within the graph structure, and semantic noise denotes inaccurate node representations derived from ambiguous node features such as textual vagueness or semantic ambiguity. In this paper, we address this problem for the first time via theoretical analyses and empirical evaluations. We discover that existing differentiable GNAS methods typically select architectures based on task-relevant information hidden in the graph, being highly sensitive to structural and semantic noise, which results in suboptimal selection of GNN architectures under noise. To handle the structural and semantic noise, we propose Curriculum-GraphLLM, a novel graphLLM framework for joint optimization of architectures, structures, and texts for denoised graph neural architecture search. The core idea is to jointly optimize GNN architectures, graph structures, and textual semantics as a unified denoising process during architecture search. Specifically, we first develop a dynamic topology updating mechanism to adaptively adjust the graph structure. Then, we jointly optimize the GNN architecture and graph structure through a curriculum-based iterative updating approach. To further deal with semantic noise on text-attributed graphs (TAGs), we introduce LLMs as an auxiliary text modeling module to refine textual semantics and guide the co-optimization of text representations, graph structures, and GNN architectures. We conduct extensive experiments to show that our proposed Curriculum-GraphLLM achieves consistently competitive or superior performance compared with existing baselines, especially under structural and semantic noise.
Xin Wang, Haibo Chen, Linxin Xiao et al.· IEEE Transactions on Pattern...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
