We introduce À-la-carte Prompt Tuning (APT), a transformer-based scheme to
tune prompts on distinct data so that they can be arbitrarily composed at
inference time. The individual prompts can be trained in isolation, possibly on
different devices, at different times, and on different distributions or
domains. Furthermore each prompt only contains information about the subset of
data it was exposed to during training. During inference, models can be
assembled based on arbitrary selections of data sources, which we call
"à-la-carte learning". À-la-carte learning enables constructing bespoke
models specific to each user's individual access rights and preferences. We can
add or remove information from the model by simply adding or removing the
corresponding prompts without retraining from scratch. We demonstrate that
à-la-carte built models achieve accuracy within $5\%$ of models trained on
the union of the respective sources, with comparable cost in terms of training
and inference time. For the continual learning benchmarks Split CIFAR-100 and
CORe50, we achieve state-of-the-art performance.

使用基于 transformer 的方案进行 prompt 调整，实现任意组合，达到 bespoke models，维护各用户的访问权限和偏好，多次添加或删除相关 prompt 可达到记录更新，实现 Split CIFAR-100 和 CORe50 的反复学习监测，并得到最先进的效果。