发表机构
Beihang University（北京航空航天大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对图-文本模型持续适应中新类别推翻历史预测及严格响应保持阻碍学习的问题，提出分层响应保持（HiRP），通过分层响应保留历史区分并允许新类适应，在三个类增量设置中平均准确率提升1.84-7.95个百分点。
AI 中文摘要
预训练的图-文本模型将图表示与文本语义对齐，从而能够识别未见过的类别并跨图域进行迁移。然而，随着图数据和类别持续到来，模型应在学习新监督信息的同时保留其零样本迁移能力和历史任务知识。这带来两个挑战：（i）尽管历史类别之间的区分被保留，新类别仍可能推翻历史预测；（ii）过于严格的响应保持会阻碍新类别的学习。为应对这些挑战，我们提出分层响应保持（HiRP）。HiRP通过一个分层响应来表示这种竞争：保持每个历史类别的概率，并对新类别的概率求和，从而在保留历史区分和聚合竞争的同时，允许新类别组内部的区分进行适应。它进一步利用该响应诱导的几何结构来指导受约束的更新，在控制响应漂移的同时保留有用的适应方向。在三个类增量设置中，HiRP在每种设置下相较于最强对比基线实现了平均准确率1.84至7.95个百分点的绝对提升，同时缓解了零样本迁移性能的下降。
英文摘要
Pretrained graph-text models align graph representations with textual semantics, enabling recognition of unseen classes and transfer across graph domains. However, as graph data and classes continually arrive, models should learn from new supervision while retaining their zero-shot transfer capabilities and historical task knowledge. Two challenges arise: (i) new classes can overturn historical predictions despite preserved distinctions among historical classes, and (ii) overly strict response preservation can stall learning of new classes. To address these challenges, we propose Hierarchical Response Preservation (HiRP). HiRP represents this competition through a hierarchical response that keeps each historical-class probability and sums new-class probabilities, preserving historical distinctions and aggregate competition while allowing distinctions within the new class group to adapt. It further uses the geometry induced by this response to guide constrained updates, retaining useful adaptation directions while controlling response drift. Across three class-incremental settings, HiRP achieves absolute gains of 1.84-7.95 percentage points in average accuracy over the strongest compared baseline in each setting, while mitigating zero-shot transfer degradation.
CommentsPreprint
