让推荐模型不依赖单一模态，提升真实场景下的稳定性。
Sequential Modality Dropout for Robust Multi-Modal Sequential Recommendation
- 训练时随机丢弃用户历史中的图像或文本模态，逼模型学会无依赖预测。
- 在95%数据缺失情况下，保留61%的推荐准确率，比基线高2.8倍。
- 代码仅四行，适配多种模型，适合部署中模态缺失的推荐系统。
多模态序列推荐模型假设每个商品都有完整图文信息，但真实电商数据常缺图或缺文。若模型在训练时用全模态数据，部署时缺失某模态则性能骤降。本文提出序列模态丢弃（SMD）：训练时以概率p独立随机删除整个用户行为序列中的图像或文本流，使模型学会不依赖任一模态进行下一商品预测。通过保留率（test-time移除模态后仍保持的HR@10比例）衡量鲁棒性。在四个Amazon领域、四种主干模型（MM-SASRec、IISAN、MISSRec、fMRLRec）上，SMD使文本保留率提升1.0至3.2倍，几乎不影响全模态准确率；当每项缺失率达95%时，保留率从22%提升至61%（2.8倍）。引入跨模态重建损失可进一步将保留率从90%提升至98%。SMD仅需四行代码，与架构无关，显著提升模型在真实缺失模态场景下的鲁棒性。
原文摘要 · Abstract (English)
Multi-modal sequential recommenders assume every item carries every modality, but real product catalogs often miss images or text, and a model trained on complete data loses much of its recommendation accuracy when a modality is unavailable at serving time. We propose Sequential Modality Dropout (SMD): during training, each modality stream (image and text) is independently erased with probability p for an entire user interaction history, so the model learns to predict the next item without relying on any single modality. We measure robustness by retention, the fraction of a model's full-modality accuracy (HR@10) that survives when a modality is removed at test time. Across four backbones (MM-SASRec, IISAN, MISSRec, and fMRLRec) on four Amazon domains, SMD raises text retention by 1.0 to 3.2x at essentially no cost to full-modality accuracy; under an extreme 95% per-item missing rate, it retains 61% of HR@10 versus 22% without (a 2.8x improvement). An optional cross-modal reconstruction loss further lifts retention from 90% to 98% on a simple additive backbone under severe text missingness. SMD is a four-line, architecture-agnostic change that makes multi-modal sequential recommenders robust to the missing modalities they actually encounter in deployment.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。