发表机构
University of Amsterdam; Aarhus University（阿姆斯特丹大学; 奥胡斯大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究多模态知识图谱中难以区分相似实体的问题，提出Time Imprint框架将时间视为实体级模态，通过三视图对比目标联合对齐多模态表示，还研究时间戳选择与聚合，实验表明该方法提升了链接预测性能，明确了时间作为模态的优势及条件。
AI 中文摘要
多模态知识图谱（MMKGs）通过文本和图像等多种模态丰富实体，但具有高度相似多模态特征的实体仍难以区分。实体的时间信息可作为额外模态来消除此类实体的歧义，但现有方法很少将时间视为与文本和图像并列的单独模态，存在稀疏时间语义阻碍与更丰富模态对齐以及多个时间戳在表示学习中引入噪声或降低鲁棒性这两个主要挑战。为应对这些挑战，我们提出Time Imprint框架，将时间视为实体级模态，通过三视图对比目标联合对齐时间、文本和视觉表示。此外，为减轻多时间戳歧义，Time Imprint研究紧凑时间戳子集选择设计空间，并通过注意力池化将所选时间戳聚合为有判别力的时间嵌入，平衡时间特异性和鲁棒性。在三个MMKG基准上的实验表明，Time Imprint实现了当前最优的链接预测性能，整体上Hits@1最多提高6.07%，在 top-1%歧义样本子集上增益高达58%。我们还研究了不同融合策略以及对时间戳可用性和质量的敏感性，阐明何时以及为何将时间作为模态最有益，同时仅增加适度的训练开销。我们在这个https URL上发布了代码。
英文摘要
Multi-Modal Knowledge Graphs (MMKGs) enrich entities with multiple modalities such as text and images, yet entities with highly similar multi-modal features remain difficult to distinguish. Temporal information of an entity can serve as an additional modality to disambiguate such entities, but existing approaches rarely treat time as a separate modality alongside text and images due to two major challenges: (1) sparse temporal semantics, which hinder alignment with richer modalities, and (2) multiple timestamps, which introduce noise or reduce robustness in representation learning. To address these challenges, we propose Time Imprint, a framework that treats time as an entity-level modality and jointly aligns temporal, textual, and visual representations via a three-view contrastive objective. Additionally, to mitigate multi-timestamp ambiguity, Time Imprint studies a compact timestamp subset selection design space and aggregates the selected timestamps into a discriminative temporal embedding with attention pooling, balancing temporal specificity and robustness. Experiments on three MMKG benchmarks demonstrate that Time Imprint achieves state-of-the-art link prediction performance, improving Hits@1 by up to 6.07\% overall and yielding up to 58\% gains on the subset of the top-1\% ambiguity samples. We further examine different fusion strategies and the sensitivity to timestamp availability and quality, clarifying when and why time-as-modality is most beneficial, while adding only modest training overhead. We release our code at https://anonymous.4open.science/r/Time-Imprint.
