Recommendation unlearning is an emerging task to serve users for erasing unusable data (e.g., some historical behaviors) from a well-trained recommender model. Existing methods process unlearning requests by fully or partially retraining the model after removing the unusable data. However, these methods are impractical due to the high computation cost of full retraining and the highly possible performance damage of partial training. In this light, a desired recommendation unlearning method should obtain a similar model as full retraining in a more efficient manner, i.e., achieving complete, efficient and innocuous unlearning. In this work, we propose an Influence Function-based Recommendation Unlearning (IFRU) framework, which efficiently updates the model without retraining by estimating the influence of the unusable data on the model via the influence function. In the light that recent recommender models use historical data for both the constructions of the optimization loss and the computational graph (e.g., neighborhood aggregation), IFRU jointly estimates the direct influence of unusable data on optimization loss and the spillover influence on the computational graph to pursue complete unlearning. Furthermore, we propose an importance-based pruning algorithm to reduce the cost of the influence function. IFRU is innocuous and applicable to mainstream differentiable models. Extensive experiments demonstrate that IFRU achieves more than250times acceleration compared to retraining-based methods with recommendation performance comparable to full retraining.

翻译：推荐遗忘是一项新兴任务，旨在从已训练好的推荐模型中擦除不可用数据（如部分历史行为）。现有方法通过移除不可用数据后对模型进行完全或部分重训练来处理遗忘请求。然而，这些方法因完全重训练的高计算成本和部分训练可能导致的性能严重下降而缺乏实用性。为此，理想的推荐遗忘方法应以更高效的方式获得与完全重训练相似的模型，即实现完整、高效且无害的遗忘。本文提出基于影响函数的推荐遗忘框架（IFRU），通过影响函数估计不可用数据对模型的影响，无需重训练即可高效更新模型。鉴于当前推荐模型同时利用历史数据构建优化损失和计算图（如邻居聚合），IFRU联合估计不可用数据对优化损失的直接影响和对计算图的溢出影响，以实现完整遗忘。此外，我们提出基于重要性的剪枝算法以降低影响函数的计算成本。IFRU具有无害性，适用于主流可微分模型。大量实验表明，相较于基于重训练的方法，IFRU可实现超过250倍的加速，且推荐性能与完全重训练相当。