发表机构
Konkuk University（建国大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
LiFTER是用于连续时间动态图预测的神经符号模型，可实现可验证计算，在四个基准中表现优异，还能分离模型各部分贡献并重构预测结果。
AI 中文摘要
连续时间动态图（CTDG）模型通过将过去的交互压缩为神经状态来预测未来的链接，尽管该方法对预测有效，但这种计算过程会模糊哪些实体在事件间共享，以及时间模式如何对预测产生贡献。我们将这一差距视为预测架构的固有属性，而非预测后需要解决的问题。链接事实时间规则诱导器（LiFTER）是一种神经符号预测器，它将观察到的交互保留为接地时间事实，并对预查询事实应用可执行的时间规则。每个分数是规则执行的带符号总和，这些规则的历史事实、实体绑定和时间顺序都得到明确满足。因此，负责预测的证据和规则可以被检查、独立重新计算和干预。在四个CTDG基准测试中，LiFTER实现了具有竞争力的历史负预测性能，并达到最高的宏观解释准确率和删除保真度。该架构还可作为一种显微镜，分离循环、历史位置和转换在不同数据集上的贡献，并将其追溯到单个事实。独立执行可重构19664个测试预测的所有对数几率，最大误差为0.0000131。LiFTER将未来链接预测转变为可验证的接地计算。
英文摘要
Aggregate performance on continuous-time dynamic graphs (CTDGs) combines, in a single score, the portion attributable to known temporal regularities and the additional predictive power of neural models. This study separates the two at the query level. We construct a mechanism-constrained predictor that uses pair recurrence, recency and history position, renewal patterns, and short sequential transitions while learning the compatibility within each mechanism. Across four CTDG datasets, this predictor recovers a substantial portion of the performance of strong neural baselines, and the recovered performance quickly saturates with a small, dataset-specific set of explicit mechanisms. Neural residuals concentrate on queries for which the positive and negative candidates have similar mechanism-execution profiles. Allowing conditional interactions among mechanisms is more effective than simply reweighting their existing contributions. Conditioning the contribution of one mechanism on the execution state of another recovers 54.9-73.2% of the original neural-only queries and improves overall paired accuracy on all four datasets. Although the magnitude of the effect varies across datasets, these results show that the performance gap of neural CTDG models need not be treated solely as an opaque difference in representational capacity. At least part of the gap is localized to queries with similar candidate execution profiles and can be functionally explained by conditional coordination among known, low-dimensional mechanisms.
