arXiv Machine Learning

TailSpec-EASE: Knowledge-Graph-Regularized Linear Recommendation for Web Long-Tail Discovery

TailSpec-EASE is a lightweight linear recommender that incorporates a relation‑aware spectral knowledge‑graph prior into a local closed‑form reconstruction objective. By adapting the prior strength to item popularity, it provides stronger semantic guidance for long‑tail items. Across four public benchmarks, it achieves a favorable balance of overall accuracy, long‑tail performance, and training cost, improving NDCG@20 by up to 24% over a no‑KG baseline and training in just 37 seconds on CPU compared to thousands of seconds for GPU‑based KGAT and CPU LightGCN.

arXiv Machine Learning
Nov 5

Item Representations Matter: Bridging Hard Semantic IDs and Soft Prototype Mixtures for Generative Retrieval

The paper introduces CAP‑Mix, a flow‑based recommender that represents items as soft mixtures of shared prototypes plus item‑specific vectors, allowing continuous models to capture shared structure without discretization. CAP‑Mix jointly trains assignments, prototypes, and item vectors, optionally leveraging pretrained Semantic ID responsibilities or full content embeddings. Across three datasets, CAP‑Mix outperforms flat lookup tables—especially on sparse Amazon datasets—and achieves significant gains in HR@5 and NDCG@5 while delivering up to 161× faster inference than discrete baselines.

By Vicente Balmaseda, Dongqi Fu, Jiarui Feng, Ren chen, Hanqing Zeng, Tianxin Wei, Yinglong Xia, Tianbao Yang, Hong Li
arXiv Machine Learning
Jun 30

Diagnosing and Mitigating Retrieval Bottlenecks in LLM-Based Cold-Start Recommendation

arXiv:2606. 29947v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as rerankers in recommender systems, with the expectation that semantic understanding will help in cold-start and long-tail regimes.

By Zhe Dong (University of Maine at Presque Isle), Fang Qin (Stanford University), Manish Shah (Independent Researcher), Yicheng Wang (Independent Researcher)
arXiv Machine Learning
Sep 24

The Recall Ceiling of LLM Recommendation Reranking

The paper examines LLM-based recommendation rerankers that are often evaluated under an oracle protocol, which guarantees the ground-truth item is present in the scored set. Across Amazon datasets, this protocol overestimates realistic NDCG@10 by 92–95% because realistic retrieval only covers 2–19% of relevant items at K=100, creating a recall ceiling that limits any closed-candidate reranker's top‑k NDCG. The authors find that various optimisation strategies—including prompt engineering, model scaling, sequential models, supervised neural rerankers, LoRA fine‑tuning, hybrid retrieval, score‑aware prompting, and LLM+CF fusion—do not significantly improve over a collaborative‑filtering baseline under realistic retrieval, and they propose a Recall‑Aware Evaluation Protocol (RAEP) to better assess rerankers in low‑recall regimes.

By Zhaohui Wang
arXiv AI
Sep 7

Continual Graph Memory for Adaptive Recommendation under Intent Drift

The paper introduces CGM-Rec, a continual graph memory framework designed for adaptive recommendation in the presence of intent drift. CGM-Rec treats the knowledge graph as writable memory, comprising a conservative Semantic Graph Memory for stable relational knowledge and a fast-reactive Episodic Lesson Memory for recent outcomes and corrective hints. Experiments show that, with frozen model parameters and one-pass reranking, CGM-Rec outperforms neural and LLM-based baselines across multiple recommendation settings, achieving significant gains such as a 29.58% improvement in HR@1 over the strongest LLM baseline on Bundle.

By Hao Nguyen Ngoc, Tung Nguyen, Nguyen Thi Hanh, Hoang Thai Dinh, Nguyen Xuan Tung
arXiv AI
Oct 15

Personalized LLM Recommendation with Semantic IDs: Autoregressive Beam Search vs. Multi-Token Prediction

arXiv:2610.15864v1 Announce Type: cross Abstract: Large-scale personalization is shifting from embedding-table retrieval to LLM-based recommenders that generate the Semantic ID (SID) of the item to r...

By Sejoon Oh, Fernando Amat Gil, Evan Smothers, Dan Iter, Mark Thornburg, Dawit Mureja Argaw, Sourabh Medapati, Thea Wang, Ria Verma, Qiuling Xu, Harshit Syal, Ehsan Gholami, Moumita Bhattacharya, Ashish Rastogi
arXiv Machine Learning
Sep 22

Connected Content Retriever: Dense Graph Edge Features Powering Pre-Ranking at LinkedIn

The paper introduces Connected Content Retriever (CC Retriever), a pre‑ranking system for LinkedIn’s Feed that uses dense graph edge features to score candidate content from a billion‑scale index within a 120 ms latency budget. By leveraging GPU‑based sorted‑search primitives, the system can apply a full deep ranking model with 50× more parameters, achieving a 2.5% lift in content time spent in online experiments. The work details the economic‑graph features and model architecture that enable this scalable, low‑latency scoring pipeline.

By Akhilesh Gupta, Sudarshan Srinivasa Ramanujam, Chirag Bhanuprasad Mehta, Reshma Asharaf Beena, Dhritiman Das, Birjodh Singh Tiwana, Bhargavkumar Kanubhai Patel, Mack Lee, Renyi Tang
arXiv AI
Jun 18

RankGraph-2: Lifecycle Co-Design for Billion-Node Graph Learning in Recommendation

arXiv:2606. 18379v1 Announce Type: cross Abstract: Graph-based retrieval at billion-node scale requires jointly solving three tightly coupled problems -- graph construction, representation learning, and real-time serving -- yet existing work addresses each in isolation.

By Renzhi Wu, Zikun Cui, Junjie Yang, Tai Guo, Hong Li, Xian Chen, Li Yu, Ke Pan, Sri Reddy, Mahesh Srinivasan, Nipun Mathur, Haomin Yu, Hong Yan
arXiv Machine Learning
Aug 11

PreGress: Ranking-Native Pre-training and Prompting for Graph Node Ranking

arXiv:2608. 09016v1 Announce Type: cross Abstract: Node ranking is a fundamental problem in graph information retrieval, measuring the relative importance of nodes and supporting a wide range of applications such as influence analysis, recommendation, and graph-based retrieval augmented generation.

By Lujie Ban, Jiasheng shi, Yingli Zhou, Kaiwen Xue, Daiyin Wang, Xubin Li, Shuanghua Li, Chenhao Ma