OPBench: A Graph Benchmark to Combat the Opioid Crisis
Tianyi Ma, Yiyang Li, Yiyue Qian, Zheyuan Zhang, Zehong Wang, Chuxu Zhang, Yanfang Ye
TL;DR
The paper addresses the lack of a standardized benchmark for graph learning in the opioid crisis. It proposes OPBench, a first-of-its-kind benchmark with five datasets spanning healthcare, social networks, and dietary data, incorporating heterogeneous graphs and hypergraphs. The authors provide a unified evaluation framework with predefined splits, reproducible baselines, and comprehensive experiments that show higher-order and heterogeneous models outperform homogeneous projections, and data-imbalance handling is crucial. The work includes open-source code and datasets to foster reproducible, fair comparisons and accelerate graph-based interventions in public health.
Abstract
The opioid epidemic continues to ravage communities worldwide, straining healthcare systems, disrupting families, and demanding urgent computational solutions. To combat this lethal opioid crisis, graph learning methods have emerged as a promising paradigm for modeling complex drug-related phenomena. However, a significant gap remains: there is no comprehensive benchmark for systematically evaluating these methods across real-world opioid crisis scenarios. To bridge this gap, we introduce OPBench, the first comprehensive opioid benchmark comprising five datasets across three critical application domains: opioid overdose detection from healthcare claims, illicit drug trafficking detection from digital platforms, and drug misuse prediction from dietary patterns. Specifically, OPBench incorporates diverse graph structures, including heterogeneous graphs and hypergraphs, to preserve the rich and complex relational information among drug-related data. To address data scarcity, we collaborate with domain experts and authoritative institutions to curate and annotate datasets while adhering to privacy and ethical guidelines. Furthermore, we establish a unified evaluation framework with standardized protocols, predefined data splits, and reproducible baselines to facilitate fair and systematic comparison among graph learning methods. Through extensive experiments, we analyze the strengths and limitations of existing graph learning methods, thereby providing actionable insights for future research in combating the opioid crisis. Our source code and datasets are available at https://github.com/Tianyi-Billy-Ma/OPBench.