arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2210.13005cs.LGcs.IR
收藏

面向分布外序列事件预测:一种因果处理

Towards Out-of-Distribution Sequential Event Prediction: A Causal Treatment

Shanghai Jiao Tong University(上海交通大学);DAMO Academy, Alibaba Group(阿里巴巴集团达摩院);Shanghai AI Laboratory(上海人工智能实验室)

Chenxiao Yang, Qitian Wu, Qingsong Wen, Zhiqiang Zhou, Liang Sun, Junchi Yan

摘要:

序列事件预测的目标是基于一系列历史事件来估计下一个事件,其应用于序列推荐、用户行为分析和临床治疗。在实践中,下一事件预测模型是用一次收集的序列数据训练的,并且需要推广到遥远未来新到达的序列,这要求模型处理从训练到测试的时间分布偏移。在本文中,我们首先从数据生成的角度揭示了一个负面的结果,即现有的最大似然估计方法由于潜在的上下文混淆而导致分布偏移失败,即,历史事件和下一个事件的共同原因。然后,我们设计了一个基于后门调整的新学习目标,并进一步利用变分推理使其易于处理序列学习问题。最重要的是,我们提出了一个框架与层次分支结构学习上下文特定的表示。针对不同任务的综合实验(例如,顺序推荐)证明了我们的方法的有效性,适用性和可扩展性与各种现成的模型作为骨干。

英文摘要:

The goal of sequential event prediction is to estimate the next event based on a sequence of historical events, with applications to sequential recommendation, user behavior analysis and clinical treatment. In practice, the next-event prediction models are trained with sequential data collected at one time and need to generalize to newly arrived sequences in remote future, which requires models to handle temporal distribution shift from training to testing. In this paper, we first take a data-generating perspective to reveal a negative result that existing approaches with maximum likelihood estimation would fail for distribution shift due to the latent context confounder, i.e., the common cause for the historical events and the next event. Then we devise a new learning objective based on backdoor adjustment and further harness variational inference to make it tractable for sequence learning problems. On top of that, we propose a framework with hierarchical branching structures for learning context-specific representations. Comprehensive experiments on diverse tasks (e.g., sequential recommendation) demonstrate the effectiveness, applicability and scalability of our method with various off-the-shelf models as backbones.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑