发表机构
Amazon; North Carolina State University; Bangladesh University of Engineering and Technology（亚马逊; 北卡罗来纳州立大学; 孟加拉工程技术大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对慈善食品机构食品替代的多目标需求，提出异构图神经网络框架，利用大规模公共数据构建关系图，在稀疏性与冷启动场景下实现更优的替代推荐，为机构决策提供支持。
AI 中文摘要
慈善食品机构通过向有需要的人群分发捐赠食品，在缓解粮食不安全方面发挥着重要作用。然而，它们依赖临时实物捐赠，经常面临特定食品短缺，因此需要提供替代食品。良好的食品替代需要匹配家庭偏好、营养需求和物品相似性。由于资源限制，机构拥有的消费行为直接记录有限，这使得做出满足多个标准的适当替代决策颇具挑战。本研究提出一种异构图神经网络（HeteroGNN），这是一种面向慈善食品机构食品替代的基于源的推荐框架。我们首先从大规模公共数据源构建统一关系图，结合美国背景下的家庭食品消费行为和食品营养信息。我们将替代推荐视为具有三个目标的多目标排序问题，包括行为亲和力、健康适用性和替代相似性。我们通过从图中移除关系边，在标准图关系和不利冷启动设置下训练并验证所提出的框架。结果表明，所提出的框架在预测消费行为时利用了节点特征之外的关系信息。此外，当模型接收到不完整的行为和营养特征信息时，所提出的框架在稀疏性下仍保持稳健。最后，我们展示了不同目标之间的弱相关性，从而证明将多目标框架作为聚合决策的替代方案是合理的。所提出的框架可帮助下游慈善机构决策者在可用信息有限的情况下做出特定情境的替代推荐。
英文摘要
Charitable food agencies play an important role in alleviating food insecurity by distributing donated food to people in need. However, they rely on ad hoc in-kind donations and often face shortages of specific foods, so they offer substitutes. A good food substitution requires matching household preferences, nutritional needs, and item similarity. Agencies have limited direct records of consumption behavior due to resource constraints, making it challenging to make an appropriate substitution decision that meets multiple criteria. In this study, we propose a heterogeneous graph neural network (HeteroGNN), a source-grounded recommendation framework for food substitution in charitable food agencies. We first build a unified relational graph from large-scale public data sources, combining household behavior on food consumption and food nutrient information in the United States (US) context. We treat the substitution recommendation as a multi-objective ranking problem with three targets, including behavior affinity, health suitability, and substitution similarity. We train and validate the proposed framework under standard graph relationship and adverse cold-start settings by removing relational edges from the graph. Our results show that the proposed framework leverages relational information beyond node features in predicting consumption behavior. Additionally, the proposed framework remains robust with sparsity when the model receives incomplete information about behavior and nutrient features. Finally, we show the weak correlation among different objectives, thereby justifying the multi-objective framing as a replacement for an aggregated decision. The proposed framework can help downstream charitable agency decision-makers make contextspecific substitution recommendations with limited information available.
