The paper introduces TintCF, a method that incorporates time-aware user and item embeddings to denoise collaborative filtering models. By reweighting the adjacency matrix (Tint‑A) or the loss function (Tint‑L), the approach leverages temporal patterns to identify and correct noisy or malicious interactions. Experiments on four real‑world datasets demonstrate that incorporating time information improves model robustness and performance.
arXiv:2608.23400v1 Announce Type: cross Abstract: Discrete Diffusion Models (DDMs) have recently been introduced to recommendation systems, modeling user history as a token generation process via ite...
arXiv:2608.21243v1 Announce Type: cross Abstract: Sequential recommendation predicts the next item from a user's interaction history, but not every interaction is equally informative. Real logs combi...
arXiv:2606. 19658v1 Announce Type: new Abstract: Implicit feedback is widely used in recommender systems due to its accessibility and generality, yet it usually presents noisy samples (e.
arXiv:2608. 10983v1 Announce Type: cross Abstract: Multi-modal recommenders fuse collaborative signals with item modalities such as text, images, and audio, but the usefulness of each drifts over time and at different rates.
Discrete Diffusion Models (DDMs) have recently been introduced to recommendation systems, modeling user history as a token generation process via iterative denoising. However, while effective at captu...
Multi-modal recommenders fuse collaborative signals with item modalities such as text, images, and audio, but the usefulness of each drifts over time and at different rates. For example, chocolate purchases typically guided by textual ingredient cues can shift toward visual packaging and ambient audio around Valentine's Day.
arXiv:2606. 06225v1 Announce Type: cross Abstract: Collaborative filtering and graph-based recommendation models are highly effective because they leverage observed user interactions, but this dependence creates a fundamental cold-start challenge when newly added content has no interaction history.
arXiv:2602.23135v3 Announce Type: replace-cross Abstract: Edge classification on directed dynamic graphs is critical for understanding evolving user-item interactions and behavioral patterns in recom...
arXiv:2611.06610v1 Announce Type: new Abstract: Collaborative filtering (CF) is a cornerstone of recommender systems and plays a relevant role in many modern applications. CF uses user-item interacti...
arXiv:2606. 12245v1 Announce Type: cross Abstract: Cold-start item recommendation remains a persistent challenge in real-world systems due to the absence of interaction histories.
PRISM introduces personalized item representations in user history, allowing each item’s embedding to reflect its relationship to a specific user rather than using a shared embedding across all users. The method leverages upstream ranking computations and an autoencoder to compress user and item tower states into a single embedding per scored pair for downstream replay. Offline tests on a billion‑scale recommendation surface show a modest but measurable improvement in downstream normalized entropy, with gains scaling with sequence length according to a power‑law relationship.
The paper presents a scalable graph neural network (GNN) system for friend recommendation on a massive social graph. It introduces two key design choices: multi-hash ID embeddings that shrink the embedding table by over 98% without hurting ranking quality, and a timestamp-sorted compressed sparse row (CSR) storage with binary search that reduces temporal neighbor sampling from linear to logarithmic time. Experiments on a 194‑million‑user, 28‑billion‑edge graph show that these techniques enable production‑grade performance, boosting friend additions by 16% and unique friend adders by 11.5% in an online A/B test.