Temporal Interaction Graphs (TIGs) are widely utilized to represent real-world systems. To facilitate representation learning on TIGs, researchers have proposed a series of TIG models. However, these models are still facing two tough gaps between the pre-training and downstream predictions in their ``pre-train, predict'' training paradigm. First, the temporal discrepancy between the pre-training and inference data severely undermines the models' applicability in distant future predictions on the dynamically evolving data. Second, the semantic divergence between pretext and downstream tasks hinders their practical applications, as they struggle to align with their learning and prediction capabilities across application scenarios. Recently, the ``pre-train, prompt'' paradigm has emerged as a lightweight mechanism for model generalization. Applying this paradigm is a potential solution to solve the aforementioned challenges. However, the adaptation of this paradigm to TIGs is not straightforward. The application of prompting in static graph contexts falls short in temporal settings due to a lack of consideration for time-sensitive dynamics and a deficiency in expressive power. To address this issue, we introduce Temporal Interaction Graph Prompting (TIGPrompt), a versatile framework that seamlessly integrates with TIG models, bridging both the temporal and semantic gaps. In detail, we propose a temporal prompt generator to offer temporally-aware prompts for different tasks. These prompts stand out for their minimalistic design, relying solely on the tuning of the prompt generator with very little supervision data. To cater to varying computational resource demands, we propose an extended ``pre-train, prompt-based fine-tune'' paradigm, offering greater flexibility. Through extensive experiments, the TIGPrompt demonstrates the SOTA performance and remarkable efficiency advantages.

翻译：时序交互图（TIGs）广泛应用于表示现实世界系统。为促进TIGs上的表征学习，研究者提出了一系列TIG模型。然而，在"预训练-预测"训练范式下，这些模型仍面临预训练与下游预测之间的两大鸿沟。首先，预训练数据与推理数据之间的时序差异严重削弱了模型在动态演化数据上进行远期预测的适用性。其次， pretext任务与下游任务之间的语义分歧阻碍了实际应用，因为模型难以在不同应用场景中协调其学习与预测能力。近年来，"预训练-提示"范式作为一种轻量级模型泛化机制崭露头角。应用该范式是解决上述挑战的潜在方案，但将其适配至TIGs并非易事。由于缺乏对时间敏感动态特性的考量且表达能力不足，静态图场景中的提示方法在时序场景下表现欠佳。针对此问题，我们提出时序交互图提示（TIGPrompt）——一种可与TIG模型无缝集成的通用框架，同时弥合时序与语义鸿沟。具体而言，我们设计时序提示生成器为不同任务提供具有时序感知能力的提示。这些提示以极简设计著称，仅需极少监督数据即可完成提示生成器的调优。为适应不同计算资源需求，我们提出扩展的"预训练-基于提示的微调"范式，提供更大灵活性。通过大量实验，TIGPrompt展现出最优性能（SOTA）及显著效率优势。