{"total":80,"rows":[{"id":"2111.00364","title":"Sustainable AI: Environmental Implications, Challenges and Opportunities","created":"2021-10-30","cited_by_count":242,"area":null},{"id":"2208.06102","title":"Zeus: Understanding and Optimizing GPU Energy Consumption of DNN Training","created":"2022-08-12","cited_by_count":79,"area":null},{"id":"2104.05158","title":"Software-Hardware Co-design for Fast and Scalable Training of Deep Learning Recommendation Models","created":"2021-04-12","cited_by_count":78,"area":null},{"id":"2101.11714","title":"TT-Rec: Tensor Train Compression for Deep Learning Recommendation Models","created":"2021-01-25","cited_by_count":58,"area":null},{"id":"2102.00075","title":"RecSSD: Near Data Processing for Solid State Drive Based Recommendation Inference","created":"2021-01-29","cited_by_count":35,"area":null},{"id":"2108.09373","title":"Understanding Data Storage and Ingestion for Large-Scale Deep Recommendation Model Training","created":"2021-08-20","cited_by_count":28,"area":null},{"id":"2201.10095","title":"RecShard: Statistical Feature-Based Memory Optimization for Industry-Scale Neural Recommendation","created":"2022-01-25","cited_by_count":28,"area":null},{"id":"2103.00686","title":"Accelerating Recommendation System Training by Leveraging Popular Choices","created":"2021-03-01","cited_by_count":22,"area":null},{"id":"2105.01898","title":"CoSA: Scheduling by Constrained Optimization for Spatial Accelerators","created":"2021-05-05","cited_by_count":22,"area":null},{"id":"2105.11010","title":"Post-Training Sparsity-Aware Quantization","created":"2021-05-23","cited_by_count":17,"area":null},{"id":"2206.02633","title":"Towards Fair Federated Recommendation Learning: Characterizing the Inter-Dependence of System and Data Heterogeneity","created":"2022-05-30","cited_by_count":17,"area":null},{"id":"2208.06399","title":"AutoShard: Automated Embedding Table Sharding for Recommender Systems","created":"2022-08-12","cited_by_count":17,"area":null},{"id":"2209.06800","title":"MGG: Accelerating Graph Neural Networks with Fine-grained intra-kernel Communication-Computation Pipelining on Multi-GPU Platforms","created":"2022-09-14","cited_by_count":16,"area":null},{"id":"2111.10635","title":"HeterPS: Distributed Deep Learning With Reinforcement Learning Based Scheduling in Heterogeneous Environments","created":"2021-11-20","cited_by_count":15,"area":null},{"id":"2210.02023","title":"DreamShard: Generalizable Embedding Table Placement for Recommender Systems","created":"2022-10-05","cited_by_count":14,"area":null},{"id":"2310.02784","title":"MAD Max Beyond Single-Node: Enabling Large Machine Learning Model Acceleration on Distributed Systems","created":"2023-10-04","cited_by_count":14,"area":null},{"id":"2203.10135","title":"Learning Compressed Embeddings for On-Device Inference","created":"2022-03-18","cited_by_count":13,"area":null},{"id":"2204.05436","title":"Heterogeneous Acceleration Pipeline for Recommendation System Training","created":"2022-04-11","cited_by_count":13,"area":null},{"id":"2205.04702","title":"Training Personalized Recommendation Systems from (GPU) Scratch: Look Forward not Backwards","created":"2022-05-10","cited_by_count":11,"area":null},{"id":"2202.12429","title":"BagPipe: Accelerating Deep Recommendation Model Training","created":"2022-02-24","cited_by_count":10,"area":null},{"id":"2110.07554","title":"Looper: An end-to-end ML platform for product decisions","created":"2021-10-14","cited_by_count":9,"area":null},{"id":"2302.10872","title":"MP-Rec: Hardware-Software Co-Design to Enable Multi-Path Recommendation","created":"2023-02-21","cited_by_count":9,"area":null},{"id":"2105.08820","title":"RecPipe: Co-designing Models and Hardware to Jointly Optimize Recommendation Quality and Performance","created":"2021-05-18","cited_by_count":8,"area":null},{"id":"2209.01346","title":"HammingMesh: A Network Topology for Large-Scale Deep Learning","created":"2022-09-03","cited_by_count":8,"area":null},{"id":"2406.05303","title":"Beyond Efficiency: Scaling AI Sustainably","created":"2024-06-08","cited_by_count":8,"area":null},{"id":"2103.06124","title":"Semantically Constrained Memory Allocation (SCMA) for Embedding in Efficient Recommendation Systems","created":"2021-02-24","cited_by_count":7,"area":null},{"id":"2105.12676","title":"Low-Precision Hardware Architectures Meet Recommendation Model Inference at Scale","created":"2021-05-26","cited_by_count":7,"area":null},{"id":"2312.03256","title":"CAFE: Towards Compact, Adaptive, and Fast Embedding for Large-scale Recommendation Models","created":"2023-12-06","cited_by_count":7,"area":null},{"id":"2110.14812","title":"Differentiable NAS Framework and Application to Ads CTR Prediction","created":"2021-10-25","cited_by_count":6,"area":null},{"id":"2111.00680","title":"GNNear: Accelerating Full-Batch Training of Graph Neural Networks with Near-Memory Processing","created":"2021-11-01","cited_by_count":6,"area":null},{"id":"2202.11655","title":"TEE-based decentralized recommender systems: The raw data sharing redemption","created":"2022-02-23","cited_by_count":6,"area":null},{"id":"2110.11489","title":"Supporting Massive DLRM Inference Through Software Defined Memory","created":"2021-10-21","cited_by_count":5,"area":null},{"id":"2203.15837","title":"Learning to Collide: Recommendation System Model Compression with Learned Hash Functions","created":"2022-03-28","cited_by_count":5,"area":null},{"id":"2209.08938","title":"Accelerating Neural Network Inference with Processing-in-DRAM: From the Edge to the Cloud","created":"2022-09-19","cited_by_count":5,"area":null},{"id":"2301.04122","title":"Mystique: Enabling Accurate and Scalable Generation of Production AI Benchmarks","created":"2022-12-16","cited_by_count":5,"area":null},{"id":"2301.10904","title":"GPU-based Private Information Retrieval for On-Device Machine Learning Inference","created":"2023-01-26","cited_by_count":5,"area":null},{"id":"2305.01868","title":"Pre-train and Search: Efficient Embedding Table Sharding with Pre-trained Neural Cost Models","created":"2023-05-03","cited_by_count":5,"area":null},{"id":"2310.18481","title":"MOSEL: Inference Serving Using Dynamic Modality Selection","created":"2023-10-27","cited_by_count":5,"area":null},{"id":"2108.02191","title":"Random Offset Block Embedding Array (ROBE) for CriteoTB Benchmark MLPerf DLRM Model : 1000$\\times$ Compression and 3.1$\\times$ Faster Inference","created":"2021-08-04","cited_by_count":4,"area":null},{"id":"2301.02959","title":"FlexShard: Flexible Sharding for Industry-Scale Sequence Recommendation Models","created":"2023-01-08","cited_by_count":4,"area":null},{"id":"2402.07529","title":"Accelerating Distributed Deep Learning using Lossless Homomorphic Compression","created":"2024-02-12","cited_by_count":4,"area":null},{"id":"2406.13941","title":"UpDLRM: Accelerating Personalized Recommendation using Real-World PIM Architecture","created":"2024-06-20","cited_by_count":4,"area":null},{"id":"2105.01064","title":"Alternate Model Growth and Pruning for Efficient Training of Recommendation Systems","created":"2021-05-04","cited_by_count":3,"area":null},{"id":"2210.05889","title":"KAIROS: Building Cost-Efficient Machine Learning Inference Systems with Heterogeneous Cloud Resources","created":"2022-10-12","cited_by_count":3,"area":null},{"id":"2301.09262","title":"AttMEMO : Accelerating Transformers with Memoization on Big Memory Systems","created":"2023-01-23","cited_by_count":3,"area":null},{"id":"2305.07205","title":"Mem-Rec: Memory Efficient Recommendation System using Alternative Representation","created":"2023-05-12","cited_by_count":3,"area":null},{"id":"2308.08500","title":"InTune: Reinforcement Learning-based Data Pipeline Optimization for Deep Recommendation Models","created":"2023-08-13","cited_by_count":3,"area":null},{"id":"2308.14902","title":"Ad-Rec: Advanced Feature Interactions to Address Covariate-Shifts in Recommendation Networks","created":"2023-08-28","cited_by_count":3,"area":null},{"id":"2312.11742","title":"ACCL+: an FPGA-Based Collective Engine for Distributed Applications","created":"2023-12-18","cited_by_count":3,"area":null},{"id":"2112.11022","title":"Synthetic Data and Simulators for Recommendation Systems: Current State and Future Directions","created":"2021-12-21","cited_by_count":2,"area":null},{"id":"2202.13481","title":"PARIS and ELSA: An Elastic Scheduling Algorithm for Reconfigurable Multi-GPU Inference Servers","created":"2022-02-27","cited_by_count":2,"area":null},{"id":"2207.10731","title":"The trade-offs of model size in large recommendation models : A 10000 $\\times$ compressed criteo-tb DLRM model (100 GB parameters to mere 10MB)","created":"2022-07-21","cited_by_count":2,"area":null},{"id":"2211.16648","title":"COMET: A Comprehensive Cluster Design Methodology for Distributed Deep Learning Training","created":"2022-11-30","cited_by_count":2,"area":null},{"id":"2307.01292","title":"Pareto-Secure Machine Learning (PSML): Fingerprinting and Securing Inference Serving Systems","created":"2023-07-03","cited_by_count":2,"area":null},{"id":"2406.14571","title":"PreSto: An In-Storage Data Preprocessing System for Training Recommendation Models","created":"2024-06-11","cited_by_count":2,"area":null},{"id":"2410.20046","title":"DQRM: Deep Quantized Recommendation Models","created":"2024-10-26","cited_by_count":2,"area":null},{"id":"2207.11434","title":"RIBBON: Cost-Effective and QoS-Aware Deep Learning Model Inference using a Diverse Pool of Cloud Computing Instances","created":"2022-07-23","cited_by_count":1,"area":null},{"id":"2212.06264","title":"Data Leakage via Access Patterns of Sparse Features in Deep Learning-based Recommendation Systems","created":"2022-12-12","cited_by_count":1,"area":null},{"id":"2303.17727","title":"BOLT: An Automated Deep Learning Framework for Training and Deploying Large-Scale Search and Recommendation Models on Commodity CPU Hardware","created":"2023-03-30","cited_by_count":1,"area":null},{"id":"2307.10244","title":"Evaluating and Enhancing Robustness of Deep Recommendation Systems Against Hardware Errors","created":"2023-07-17","cited_by_count":1,"area":null},{"id":"2308.08406","title":"Content-based Recommendation Engine for Video Streaming Platform","created":"2023-08-16","cited_by_count":1,"area":null},{"id":"2404.08847","title":"LazyDP: Co-Designing Algorithm-Software for Scalable Training of Differentially Private Recommendation Models","created":"2024-04-12","cited_by_count":1,"area":null},{"id":"2409.16633","title":"PIFS-Rec: Process-In-Fabric-Switch for Large-Scale Recommendation System Inferences","created":"2024-09-25","cited_by_count":1,"area":null},{"id":"2410.00215","title":"Characterizing and Efficiently Accelerating Multimodal Generation Model Inference","created":"2024-09-30","cited_by_count":1,"area":null},{"id":"2410.12794","title":"Disaggregating Embedding Recommendation Systems with FlexEMR","created":"2024-09-28","cited_by_count":1,"area":null},{"id":"2512.12295","title":"Near-Zero-Overhead Freshness for Recommendation Systems via Inference-Side Model Updates","created":"2025-12-13","cited_by_count":1,"area":null},{"id":"2104.01981","title":"ECRM: Efficient Fault Tolerance for Recommendation Model Training via Erasure Coding","created":"2021-04-05","cited_by_count":0,"area":null},{"id":"2107.12024","title":"Leaf-FM: A Learnable Feature Generation Factorization Machine for Click-Through Rate Prediction","created":"2021-07-26","cited_by_count":0,"area":null},{"id":"2302.11750","title":"Hera: A Heterogeneity-Aware Multi-Tenant Inference Server for Personalized Recommendations","created":"2023-02-23","cited_by_count":0,"area":null},{"id":"2402.04032","title":"ProactivePIM: Accelerating Weight-Sharing Embedding Layer with PIM for Scalable Recommendation System","created":"2024-02-06","cited_by_count":0,"area":null},{"id":"2406.06955","title":"ElasticRec: A Microservice-based Model Serving Architecture Enabling Elastic Resource Scaling for Recommendation Models","created":"2024-06-11","cited_by_count":0,"area":null},{"id":"2410.22249","title":"Pushing the Performance Envelope of DNN-based Recommendation Systems Inference on GPUs","created":"2024-10-29","cited_by_count":0,"area":null},{"id":"2501.12032","title":"Accelerating Recommender Model ETL with a Streaming FPGA-GPU Dataflow","created":"2025-01-21","cited_by_count":0,"area":null},{"id":"2504.00520","title":"SCRec: A Scalable Computational Storage System with Statistical Sharding and Tensor-train Decomposition for Recommendation Models","created":"2025-04-01","cited_by_count":0,"area":null},{"id":"2504.09870","title":"Ember: A Compiler for Efficient Embedding Operations on Decoupled Access-Execute Architectures","created":"2025-04-14","cited_by_count":0,"area":null},{"id":"2507.01676","title":"Deep Recommender Models Inference: Automatic Asymmetric Data Flow Optimization","created":"2025-07-02","cited_by_count":0,"area":null},{"id":"2512.19342","title":"Faster Distributed Inference-Only Recommender Systems via Bounded Lag Synchronous Collectives","created":"2025-12-22","cited_by_count":0,"area":null},{"id":"2604.18351","title":"Balanced Co-Clustering of Users and Items for Embedding Table Compression in Recommender Systems","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2606.22013","title":"Load Testing for Machine Learning Model Serving Systems at Scale","created":"2026-06-20","cited_by_count":0,"area":null},{"id":"2607.25110","title":"Memory Layer: Train the In-Model Cache for Recommendation Models","created":"2026-07-27","cited_by_count":0,"area":null}],"next_cursor":null}