{"total":17,"rows":[{"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":"2204.05436","title":"Heterogeneous Acceleration Pipeline for Recommendation System Training","created":"2022-04-11","cited_by_count":13,"area":null},{"id":"2201.07821","title":"Building a Performance Model for Deep Learning Recommendation Model Training on GPUs","created":"2022-01-19","cited_by_count":10,"area":null},{"id":"2104.05755","title":"Tensor Processing Primitives: A Programming Abstraction for Efficiency and Portability in Deep Learning & HPC Workloads","created":"2021-04-12","cited_by_count":9,"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":"2305.07205","title":"Mem-Rec: Memory Efficient Recommendation System using Alternative Representation","created":"2023-05-12","cited_by_count":3,"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":"2204.10943","title":"FPGA-based AI Smart NICs for Scalable Distributed AI Training Systems","created":"2022-04-22","cited_by_count":1,"area":null},{"id":"2206.10034","title":"Deep Learning Models on CPUs: A Methodology for Efficient Training","created":"2022-06-20","cited_by_count":1,"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":"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":"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":"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":"2306.09293","title":"[Experiments & Analysis] Evaluating the Feasibility of Sampling-Based Techniques for Training Multilayer Perceptrons","created":"2023-06-15","cited_by_count":0,"area":null},{"id":"2404.04270","title":"Accelerating Recommender Model Training by Dynamically Skipping Stale Embeddings","created":"2024-03-22","cited_by_count":0,"area":null},{"id":"2409.14912","title":"Efficient Tabular Data Preprocessing of ML Pipelines","created":"2024-09-23","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}],"next_cursor":null}