Few-shot molecular property prediction (FSMPP) is essential in drug discovery and materials design, where high-quality labeled data are often scarce and expensive to obtain. Despite the promising performance of existing methods, especially context-aware methods, they still face two-fold severe challenges with \textit{insufficient structural context modeling} \& \textit{redundant auxiliary context learning}, leading to inadequate context graph exploration and ineffective information utilization for effective molecule representation learning. To address these, in this paper, we propose a novel framework by learning on \textbf{\underline{Re}}lational and \textbf{\underline{C}}ompact c\textbf{\underline{o}}ntext \textbf{\underline{G}}raph, named \textbf{\method}, to comprehensively exploit the context graph for expressive molecular property prediction. Specifically, the proposed \method contains two core modules: a \textbf{(1) cross-property relational learning module} to better model the structural and relational context information, and a \textbf{(2) context graph information bottleneck module} to adaptively suppress irrelevant auxiliary signals for compact context information utilization, followed by a detailed theoretical demonstration regarding the importance of joint relational and compact knowledge extraction in context graphs.

翻译：小样本分子性质预测在药物发现和材料设计中至关重要，高质量标注数据往往稀缺且获取成本高昂。尽管现有方法（尤其是上下文感知方法）展现出可喜性能，但其仍面临两大严峻挑战：**结构上下文建模不足**与**冗余辅助上下文学习**，导致难以充分探索上下文图结构、无法有效利用信息进行分子表征学习。为此，本文提出一种基于关系型紧凑上下文图学习的新框架（命名为**ReCoG**），以全面挖掘上下文图信息实现高表现力的分子性质预测。具体而言，该框架包含两个核心模块：（1）跨性质关系学习模块，用于更好地建模结构性与关系性上下文信息；（2）上下文图信息瓶颈模块，通过自适应抑制无关辅助信号实现紧凑上下文信息利用。本文进一步从理论上论证了在上下文图中联合提取关系知识与紧凑知识的重要性。