Copertina

Near-Zero-Overhead Freshness for Recommendation Systems via Inference-Side Model Updates

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Yu, Wenjun, Chen, Sitian, Chen, Cheng, Zhou, Amelie Chi
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Distributed, Parallel, and Cluster Computing Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

One Pool, Two Caches: Adaptive HBM Partitioning for Accelerating Generative Recommender Serving
di: Yu, Wenjun, et al.
Pubblicazione: (2026)

Faster Distributed Inference-Only Recommender Systems via Bounded Lag Synchronous Collectives
di: Dichev, Kiril, et al.
Pubblicazione: (2025)

TaxBreak: Unmasking the Hidden Costs of LLM Inference Through Overhead Decomposition
di: Vellaisamy, Prabhu, et al.
Pubblicazione: (2026)

RcLLM: Accelerating Generative Recommendation via Beyond-Prefix KV Caching
di: Zhao, Zhan, et al.
Pubblicazione: (2026)

Lion Cub: Minimizing Communication Overhead in Distributed Lion
di: Ishikawa, Satoki, et al.
Pubblicazione: (2024)

KaMPIng: Flexible and (Near) Zero-Overhead C++ Bindings for MPI
di: Uhl, Tim Niklas, et al.
Pubblicazione: (2024)

Enabling Disaggregated Multi-Stage MLLM Inference via GPU-Internal Scheduling and Resource Sharing
di: Zhao, Lingxiao, et al.
Pubblicazione: (2025)

Checkmate: Zero-Overhead Model Checkpointing via Network Gradient Replication
di: Bhardwaj, Ankit, et al.
Pubblicazione: (2025)

Adaptive Compression in Federated Learning via Side Information
di: Isik, Berivan, et al.
Pubblicazione: (2023)

Occult: Optimizing Collaborative Communication across Experts for Accelerated Parallel MoE Training and Inference
di: Luo, Shuqing, et al.
Pubblicazione: (2025)

Harli: SLO-Aware Co-location of LLM Inference and PEFT-based Finetuning on Model-as-a-Service Platforms
di: Xu, Ao, et al.
Pubblicazione: (2025)

FedCAda: Adaptive Client-Side Optimization for Accelerated and Stable Federated Learning
di: Zhou, Liuzhi, et al.
Pubblicazione: (2024)

Reducing Communication Overhead in Federated Learning for Network Anomaly Detection with Adaptive Client Selection
di: Marfo, William, et al.
Pubblicazione: (2025)

Injecting Adrenaline into LLM Serving: Boosting Resource Utilization and Throughput via Attention Disaggregation
di: Liang, Yunkai, et al.
Pubblicazione: (2025)

InkStream: Real-time GNN Inference on Streaming Graphs via Incremental Update
di: Wu, Dan, et al.
Pubblicazione: (2023)

Characterizing WebGPU Dispatch Overhead for LLM Inference Across Four GPU Vendors, Three Backends, and Three Browsers
di: Maczan, Jędrzej
Pubblicazione: (2026)

MiCRO: Near-Zero Cost Gradient Sparsification for Scaling and Accelerating Distributed DNN Training
di: Yoon, Daegun, et al.
Pubblicazione: (2023)

Boosting Resource-Constrained Federated Learning Systems with Guessed Updates
di: Boukhari, Mohamed Yassine, et al.
Pubblicazione: (2021)

Towards Integrated Fine-tuning and Inference when Generative AI meets Edge Intelligence
di: Chen, Ning, et al.
Pubblicazione: (2024)

MUSE: Multi-Tenant Model Serving With Seamless Model Updates
di: Correia, Cláudio, et al.
Pubblicazione: (2026)

Straggler-Resilient Decentralized Learning via Adaptive Asynchronous Updates
di: Xiong, Guojun, et al.
Pubblicazione: (2023)

Bandwidth-Aware and Overlap-Weighted Compression for Communication-Efficient Federated Learning
di: Tang, Zichen, et al.
Pubblicazione: (2024)

A Joint Approach to Local Updating and Gradient Compression for Efficient Asynchronous Federated Learning
di: Song, Jiajun, et al.
Pubblicazione: (2024)

FedNMUT -- Federated Noisy Model Update Tracking Convergence Analysis
di: Chellapandi, Vishnu Pandi, et al.
Pubblicazione: (2024)

Age-of-Gradient Updates for Federated Learning over Random Access Channels
di: Wu, Yu Heng, et al.
Pubblicazione: (2024)

BGTplanner: Maximizing Training Accuracy for Differentially Private Federated Recommenders via Strategic Privacy Budget Allocation
di: Zhang, Xianzhi, et al.
Pubblicazione: (2024)

FedAR: Addressing Client Unavailability in Federated Learning with Local Update Approximation and Rectification
di: Jiang, Chutian, et al.
Pubblicazione: (2024)

Arctic Inference with Shift Parallelism: Fast and Efficient Open Source Inference System for Enterprise AI
di: Rajbhandari, Samyam, et al.
Pubblicazione: (2025)

NestPipe: Large-Scale Recommendation Training on 1,500+ Accelerators via Nested Pipelining
di: Jiang, Zhida, et al.
Pubblicazione: (2026)

HACK: Homomorphic Acceleration via Compression of the Key-Value Cache for Disaggregated LLM Inference
di: Zhang, Zeyu, et al.
Pubblicazione: (2025)

TurboGR: An Accelerated Training System for Large-Scale Generative Recommendation
di: Chai, Huichao, et al.
Pubblicazione: (2026)

Deal: Distributed End-to-End GNN Inference for All Nodes
di: Chen, Shiyang, et al.
Pubblicazione: (2025)

RelayGR: Scaling Long-Sequence Generative Recommendation via Cross-Stage Relay-Race Inference
di: Wang, Jiarui, et al.
Pubblicazione: (2026)

Designing Large Foundation Models for Efficient Training and Inference: A Survey
di: Liu, Dong, et al.
Pubblicazione: (2024)

Two-dimensional Sparse Parallelism for Large Scale Deep Learning Recommendation Model Training
di: Zhang, Xin, et al.
Pubblicazione: (2025)

Large Language Model Aided QoS Prediction for Service Recommendation
di: Liu, Huiying, et al.
Pubblicazione: (2024)

Fair Distributed Cooperative Bandit Learning on Networks for Intelligent Internet of Things Systems (Technical Report)
di: Chen, Ziqun, et al.
Pubblicazione: (2024)

Improving the End-to-End Efficiency of Offline Inference for Multi-LLM Applications Based on Sampling and Simulation
di: Fang, Jingzhi, et al.
Pubblicazione: (2025)

FUPareto: Bridging the Forgetting-Utility Gap in Federated Unlearning via Pareto Augmented Optimization
di: Wang, Zeyan, et al.
Pubblicazione: (2026)

AMDP: Asynchronous Multi-Directional Pipeline Parallelism for Large-Scale Models Training
di: Chen, Ling, et al.
Pubblicazione: (2026)