重新思考基于学习的影响力最大化：简单神经代理与原生离散搜索
Rethinking Learning-Based Influence Maximization: Simple Neural Surrogates and Native Discrete Search
浏览论文内容
中文总结 AI 辅助
该研究针对现有基于学习的影响力最大化框架的不足，提出SIMBA框架，采用轻量级神经代理与原生离散搜索，缩短求解时间并提升影响力传播与数据效率。
中文摘要 AI 辅助
现有的基于学习的影响力最大化框架严重依赖复杂的神经架构和针对种子表示的连续优化。我们提出SIMBA，一种与扩散模型无关的框架，它将轻量级神经代理与直接离散搜索相结合，以此挑战这种范式。SIMBA包含三个关键组件：1）均匀锚定的节点嵌入，可消除初始化噪声并鼓励由图拓扑和扩散模式驱动的学习；2）用于预测最终感染状态的浅层两层图神经网络代理；3）无需梯度或连续松弛即可探索组合种子空间的批量多交换模拟退火。通过将计算从复杂的表示学习转移到有效的离散搜索，SIMBA大幅缩短了求解时间，同时实现了更优的影响力传播和数据效率。我们的代码可在此https URL获取。
英文摘要
Existing learning-based influence maximization frameworks rely heavily on complex neural architectures and continuous optimization over seed representations. We challenge this paradigm with SIMBA, a diffusion-model-agnostic framework pairing a lightweight neural surrogate with direct discrete search. SIMBA introduces three key components: 1) uniformly anchored node embeddings that eliminate initialization noise and encourage learning driven by graph topology and diffusion pattern, 2) a shallow two-layer graph neural network surrogate predicting final infection states, and 3) batched multi-swap simulated annealing that explores combinatorial seed space without gradients or continuous relaxation. By shifting compute from complex representation learning to effective discrete search, SIMBA drastically cuts time-to-solution while achieving superior influence spread and data efficiency. Our code is available at https://github.com/yl489/rethink-IM.
发表机构
- UC San Diego（加利福尼亚大学圣迭戈分校）
机构由 AI 辅助整理，请以论文原文为准。
