解读动态链接预测中的时间戳置换
Interpreting Timestamp Permutations in Dynamic Link Prediction
AI 导读
一项 arXiv 研究用交叉诊断方法将时间戳置换实验中的性能差距拆分为训练条件与评估历史两类影响,并测量模型输入暴露程度。在 MOOC 数据集上,TCL 原始时序训练带来约 8.03 个 pairwise-accuracy 点的提升,而固定权重下改变历史仅带来 0.03 点;抑制显式时间编码使训练对比从 8.03 降至 3.64 点。
正文 · 原文
Abstract:Timestamp permutations are used to test whether dynamic link predictors exploit temporal information, but a performance gap can reflect changes in training, evaluation history, or both. We separate these effects with a crossed diagnostic and measure input exposure: whether altered histories actually change the predictor's inputs. On MOOC, TCL trained with binary cross-entropy gains approximately eight pairwise-accuracy points from original-chronology training under either evaluation history, while changing history at fixed weights gives only 0.03 points. The small history contrast reflects unchanged inputs for 68.37% of queries, stable rankings for most others, and cancellation of gains and losses. Under original evaluation history, suppressing explicit time encoding reduces the training contrast from 8.03 to 3.64 points, a paired reduction of 4.39 points (95% interval [3.68, 5.09]) across six seeds. DyGFormer shows corresponding training and history contrasts of 22.34 and 0.38 points across two seeds, despite greater exposure. Partial history permutations further separate nominal intervention strength, input changes, and aggregate accuracy. These comparisons turn a single permutation gap into interpretable statements about training conditions and model responses, while leaving the internal mechanisms of temporal learning open.
| Comments: | 5 pages total (ACM sigconf format). Companion code and trained models: this https URL |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Logic in Computer Science (cs.LO); Social and Information Networks (cs.SI) |
| Cite as: | arXiv:2611.23753 [cs.LG] |
| (or arXiv:2611.23753v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2611.23753 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Ilia Karpov [view email]
[v1]
Wed, 18 Nov 2026 03:08:09 UTC (73 KB)
来源:arXiv cs.AI · arxiv.org