{"list":"other","total":56,"rows":[{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1710.10903","title":"Graph Attention Networks","created":"2017-10-30","cited_by_count":8923},{"id":"1706.02216","title":"Inductive Representation Learning on Large Graphs","created":"2017-06-07","cited_by_count":6320},{"id":"1810.00826","title":"How Powerful are Graph Neural Networks?","created":"2018-10-01","cited_by_count":4393},{"id":"1903.02428","title":"Fast Graph Representation Learning with PyTorch Geometric","created":"2019-03-06","cited_by_count":2434},{"id":"1806.01973","title":"Graph Convolutional Neural Networks for Web-Scale Recommender Systems","created":"2018-06-06","cited_by_count":1138},{"id":"1603.08861","title":"Revisiting Semi-Supervised Learning with Graph Embeddings","created":"2016-03-29","cited_by_count":976},{"id":"1902.07243","title":"Graph Neural Networks for Social Recommendation","created":"2019-02-19","cited_by_count":714},{"id":"1603.04467","title":"TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems","created":"2016-03-14","cited_by_count":664},{"id":"1907.04931","title":"GraphSAINT: Graph Sampling Based Inductive Learning Method","created":"2019-07-10","cited_by_count":618},{"id":"1905.07953","title":"Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks","created":"2019-05-20","cited_by_count":541},{"id":"1811.00855","title":"Session-based Recommendation with Graph Neural Networks","created":"2018-11-01","cited_by_count":312},{"id":"1408.5093","title":"Caffe: Convolutional Architecture for Fast Feature Embedding","created":"2014-06-20","cited_by_count":288},{"id":"1512.01274","title":"MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems","created":"2015-12-03","cited_by_count":195},{"id":"2101.06861","title":"Discrete Graph Structure Learning for Forecasting Multiple Time Series","created":"2021-01-18","cited_by_count":171},{"id":"2006.10901","title":"Sparse GPU Kernels for Deep Learning","created":"2020-06-18","cited_by_count":141},{"id":"1805.08166","title":"Learning to Optimize Tensor Programs","created":"2018-05-21","cited_by_count":140},{"id":"2010.05337","title":"DistDGL: Distributed Graph Neural Network Training for Billion-Scale Graphs","created":"2020-10-11","cited_by_count":139},{"id":"1912.03264","title":"PU-GCN: Point Cloud Upsampling using Graph Convolutional Networks","created":"2019-11-30","cited_by_count":101},{"id":"2104.06700","title":"DistGNN: Scalable Distributed Training for Large-Scale Graph Neural Networks","created":"2021-04-14","cited_by_count":59},{"id":"2105.11118","title":"Dorylus: Affordable, Scalable, and Accurate GNN Training with Distributed CPU Servers and Serverless Threads","created":"2021-05-24","cited_by_count":51},{"id":"2005.03300","title":"Reducing Communication in Graph Neural Network Training","created":"2020-05-07","cited_by_count":50},{"id":"2112.08541","title":"BGL: GPU-Efficient GNN Training by Optimizing Graph Data I/O and Preprocessing","created":"2021-12-16","cited_by_count":50},{"id":"1912.12953","title":"RecNMP: Accelerating Personalized Recommendation with Near-Memory Processing","created":"2019-12-30","cited_by_count":49},{"id":"2207.04606","title":"SparseTIR: Composable Abstractions for Sparse Compilation in Deep Learning","created":"2022-07-11","cited_by_count":47},{"id":"1908.03072","title":"TensorDIMM: A Practical Near-Memory Processing Architecture for Embeddings and Tensor Operations in Deep Learning","created":"2019-08-08","cited_by_count":43},{"id":"1909.00155","title":"EnGN: A High-Throughput and Energy-Efficient Accelerator for Large Graph Neural Networks","created":"2019-08-31","cited_by_count":43},{"id":"2007.13828","title":"GRIP: A Graph Neural Network Accelerator Architecture","created":"2020-07-27","cited_by_count":37},{"id":"2104.04955","title":"A Deep Learning Based Cost Model for Automatic Code Optimization","created":"2021-04-11","cited_by_count":33},{"id":"2012.03112","title":"A Modern Primer on Processing in Memory","created":"2020-12-05","cited_by_count":32},{"id":"2102.00527","title":"A Runtime-Based Computational Performance Predictor for Deep Neural Network Training","created":"2021-01-31","cited_by_count":29},{"id":"1910.04540","title":"QPyTorch: A Low-Precision Arithmetic Simulation Framework","created":"2019-10-09","cited_by_count":22},{"id":"1903.03988","title":"Processing Data Where It Makes Sense: Enabling In-Memory Computation","created":"2019-03-10","cited_by_count":21},{"id":"2208.09151","title":"Ginex: SSD-enabled Billion-scale Graph Neural Network Training on a Single Machine via Provably Optimal In-memory Caching","created":"2022-08-19","cited_by_count":21},{"id":"1803.08601","title":"Design Principles for Sparse Matrix Multiplication on the GPU","created":"2018-03-22","cited_by_count":19},{"id":"2211.03578","title":"TLP: A Deep Learning-based Cost Model for Tensor Program Tuning","created":"2022-11-07","cited_by_count":14},{"id":"2308.00846","title":"Pathfinding Future PIM Architectures by Demystifying a Commercial PIM Technology","created":"2023-08-01","cited_by_count":14},{"id":"2205.04711","title":"SmartSAGE: Training Large-scale Graph Neural Networks using In-Storage Processing Architectures","created":"2022-05-10","cited_by_count":13},{"id":"2010.02079","title":"NATSA: A Near-Data Processing Accelerator for Time Series Analysis","created":"2020-10-05","cited_by_count":10},{"id":"2101.07557","title":"SynCron: Efficient Synchronization Support for Near-Data-Processing Architectures","created":"2021-01-19","cited_by_count":9},{"id":"2105.03814","title":"Benchmarking a New Paradigm: An Experimental Analysis of a Real Processing-in-Memory Architecture","created":"2021-05-09","cited_by_count":9},{"id":"1710.05758","title":"TensorQuant - A Simulation Toolbox for Deep Neural Network Quantization","created":"2017-10-13","cited_by_count":8},{"id":"1910.10776","title":"SMASH: Co-designing Software Compression and Hardware-Accelerated Indexing for Efficient Sparse Matrix Operations","created":"2019-10-23","cited_by_count":7},{"id":"2109.11081","title":"Sextans: A Streaming Accelerator for General-Purpose Sparse-Matrix Dense-Matrix Multiplication","created":"2021-09-22","cited_by_count":6},{"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},{"id":"2208.01243","title":"A Framework for High-throughput Sequence Alignment using Real Processing-in-Memory Systems","created":"2022-08-02","cited_by_count":5},{"id":"2310.01893","title":"SimplePIM: A Software Framework for Productive and Efficient Processing-in-Memory","created":"2023-10-03","cited_by_count":5},{"id":"2103.10836","title":"GNNerator: A Hardware/Software Framework for Accelerating Graph Neural Networks","created":"2021-03-19","cited_by_count":4},{"id":"2002.11302","title":"Bandwidth-Optimized Parallel Algorithms for Sparse Matrix-Matrix Multiplication using Propagation Blocking","created":"2020-02-26","cited_by_count":3},{"id":"2203.07673","title":"Distributed-Memory Sparse Kernels for Machine Learning","created":"2022-03-15","cited_by_count":3},{"id":"2302.04225","title":"Feature-based SpMV Performance Analysis on Contemporary Devices","created":"2023-02-08","cited_by_count":2},{"id":"2307.01684","title":"Serving Graph Neural Networks With Distributed Fog Servers For Smart IoT Services","created":"2023-07-04","cited_by_count":2},{"id":"1908.06362","title":"Near Data Acceleration with Concurrent Host Access","created":"2019-08-18","cited_by_count":1},{"id":"2303.00158","title":"HyScale-GNN: A Scalable Hybrid GNN Training System on Single-Node Heterogeneous Architecture","created":"2023-03-01","cited_by_count":1},{"id":"2306.15155","title":"SENSEi: Input-Sensitive Compilation for Accelerating GNNs","created":"2023-06-27","cited_by_count":1}],"next_cursor":null}