This article reviews the Kuaishou paper on adapting large language models for recommendation, detailing the LEARN framework's dual‑tower architecture, embedding generation, loss functions, and experimental results that address cold‑start and long‑tail challenges in modern recommender systems.
CC‑GNN addresses three drawbacks of existing graph‑neural retrieval for e‑commerce by adding content phrase nodes, scalable meta‑path message passing, and difficulty‑aware noisy contrastive learning with counterfactual augmentation, achieving up to 16 % recall improvement and notably larger gains on long‑tail queries and cold‑start items.
Didi’s engineering team analyzed a severe write bottleneck in their 3000‑node Elasticsearch cluster, identified long‑tail latency caused by refresh, translog locks, write queues and GC, and applied routing‑aware bulk writes, JVM and Lucene tweaks, and data cleaning to more than double write throughput while slashing server costs.
By consolidating each bulk request onto a single shard, tuning node write paths, and pruning unnecessary fields, Douyin’s ElasticSearch team eliminated long‑tail latency, more than doubled write throughput to over 1 million ops per second, slashed write rejections, and saved millions in infrastructure costs.
This talk presents a real-time attention-based look‑alike model (RALM) designed to address the long‑tail problem in recommendation systems by efficiently expanding seed users, leveraging user representation learning, attention mechanisms, and clustering to deliver timely, diverse content without retraining the model.
Meituan’s delivery ETA system progressed from linear regression to DeepFM, enriching user, rider, merchant, and spatiotemporal features, employing an asymmetric loss and business‑rule integration to favor early arrivals, adding a tail‑adjustment term, and is engineered with Spark‑assembled TFRecords, multi‑GPU TensorFlow training, and remote‑served TensorFlow Java inference achieving sub‑5 ms TP99 latency.
This article explains how interaction designers can use the Business Model Canvas to define and iterate product commercial strategies, outlines its nine components, showcases classic business models, and details a hands‑on workshop process that turns insights into actionable canvas drafts.
