{"list":"other","total":55,"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":"1308.3432","title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation","created":"2013-08-15","cited_by_count":2079},{"id":"1703.06103","title":"Modeling Relational Data with Graph Convolutional Networks","created":"2017-03-17","cited_by_count":1694},{"id":"1712.05877","title":"Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference","created":"2017-12-15","cited_by_count":1593},{"id":"2103.13630","title":"A Survey of Quantization Methods for Efficient Neural Network Inference","created":"2021-03-25","cited_by_count":815},{"id":"1511.00363","title":"BinaryConnect: Training Deep Neural Networks with binary weights during propagations","created":"2015-11-02","cited_by_count":592},{"id":"2003.01332","title":"Heterogeneous Graph Transformer","created":"2020-03-03","cited_by_count":582},{"id":"1606.06160","title":"DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients","created":"2016-06-20","cited_by_count":569},{"id":"2106.08295","title":"A White Paper on Neural Network Quantization","created":"2021-06-15","cited_by_count":472},{"id":"1905.03696","title":"HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-Precision","created":"2019-04-29","cited_by_count":402},{"id":"1502.02551","title":"Deep Learning with Limited Numerical Precision","created":"2015-02-09","cited_by_count":376},{"id":"1910.06188","title":"Q8BERT: Quantized 8Bit BERT","created":"2019-10-14","cited_by_count":300},{"id":"2212.12794","title":"GraphCast: Learning skillful medium-range global weather forecasting","created":"2022-12-24","cited_by_count":267},{"id":"2006.06762","title":"Ansor: Generating High-Performance Tensor Programs for Deep Learning","created":"2020-06-11","cited_by_count":201},{"id":"2010.01179","title":"The Surprising Power of Graph Neural Networks with Random Node Initialization","created":"2020-10-02","cited_by_count":198},{"id":"1812.08011","title":"Training Deep Neural Networks with 8-bit Floating Point Numbers","created":"2018-12-19","cited_by_count":164},{"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":"1511.04854","title":"A Survey of Heterogeneous Information Network Analysis","created":"2015-11-16","cited_by_count":110},{"id":"2008.05000","title":"Degree-Quant: Quantization-Aware Training for Graph Neural Networks","created":"2020-08-11","cited_by_count":96},{"id":"2106.05609","title":"GNNAutoScale: Scalable and Expressive Graph Neural Networks via Historical Embeddings","created":"2021-06-10","cited_by_count":90},{"id":"1912.12607","title":"Towards Unified INT8 Training for Convolutional Neural Network","created":"2019-12-29","cited_by_count":79},{"id":"2004.08532","title":"DGL-KE: Training Knowledge Graph Embeddings at Scale","created":"2020-04-18","cited_by_count":67},{"id":"1708.06525","title":"Neural Network-based Graph Embedding for Cross-Platform Binary Code Similarity Detection","created":"2017-08-22","cited_by_count":65},{"id":"1912.09666","title":"AdaBits: Neural Network Quantization with Adaptive Bit-Widths","created":"2019-12-20","cited_by_count":64},{"id":"2104.14129","title":"ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed Training","created":"2021-04-29","cited_by_count":61},{"id":"1906.00532","title":"Efficient 8-Bit Quantization of Transformer Neural Machine Language Translation Model","created":"2019-06-03","cited_by_count":59},{"id":"2104.06700","title":"DistGNN: Scalable Distributed Training for Large-Scale Graph Neural Networks","created":"2021-04-14","cited_by_count":59},{"id":"1802.00930","title":"Mixed Precision Training of Convolutional Neural Networks using Integer Operations","created":"2018-02-03","cited_by_count":45},{"id":"1711.02213","title":"Flexpoint: An Adaptive Numerical Format for Efficient Training of Deep Neural Networks","created":"2017-11-06","cited_by_count":44},{"id":"1904.11943","title":"SWALP : Stochastic Weight Averaging in Low-Precision Training","created":"2019-04-26","cited_by_count":42},{"id":"2007.03179","title":"GE-SpMM: General-purpose Sparse Matrix-Matrix Multiplication on GPUs for Graph Neural Networks","created":"2020-07-07","cited_by_count":42},{"id":"2110.14363","title":"VQ-GNN: A Universal Framework to Scale up Graph Neural Networks using Vector Quantization","created":"2021-10-27","cited_by_count":39},{"id":"1910.12308","title":"Asynchronous Decentralized SGD with Quantized and Local Updates","created":"2019-10-27","cited_by_count":36},{"id":"2008.11359","title":"FeatGraph: A Flexible and Efficient Backend for Graph Neural Network Systems","created":"2020-08-26","cited_by_count":36},{"id":"2012.15823","title":"Binary Graph Neural Networks","created":"2020-12-31","cited_by_count":34},{"id":"2206.11357","title":"GACT: Activation Compressed Training for Generic Network Architectures","created":"2022-06-22","cited_by_count":31},{"id":"2007.05100","title":"SGQuant: Squeezing the Last Bit on Graph Neural Networks with Specialized Quantization","created":"2020-07-09","cited_by_count":27},{"id":"2006.16423","title":"Efficient Algorithms for Device Placement of DNN Graph Operators","created":"2020-06-29","cited_by_count":24},{"id":"2106.00761","title":"Motif Prediction with Graph Neural Networks","created":"2021-05-26","cited_by_count":18},{"id":"2111.09547","title":"QGTC: Accelerating Quantized Graph Neural Networks via GPU Tensor Core","created":"2021-11-18","cited_by_count":18},{"id":"1812.11732","title":"Per-Tensor Fixed-Point Quantization of the Back-Propagation Algorithm","created":"2018-12-31","cited_by_count":15},{"id":"2009.09103","title":"C-SAW: A Framework for Graph Sampling and Random Walk on GPUs","created":"2020-09-18","cited_by_count":13},{"id":"1805.01407","title":"Scrambled Linear Pseudorandom Number Generators","created":"2018-05-03","cited_by_count":12},{"id":"2208.04529","title":"Motif-based Graph Representation Learning with Application to Chemical Molecules","created":"2022-08-09","cited_by_count":9},{"id":"2105.12676","title":"Low-Precision Hardware Architectures Meet Recommendation Model Inference at Scale","created":"2021-05-26","cited_by_count":7},{"id":"2212.04540","title":"TinyKG: Memory-Efficient Training Framework for Knowledge Graph Neural Recommender Systems","created":"2022-12-08","cited_by_count":7},{"id":"2109.08219","title":"Dr. Top-k: Delegate-Centric Top-k on GPUs","created":"2021-09-16","cited_by_count":6},{"id":"2202.08556","title":"Heuristic Adaptability to Input Dynamics for SpMM on GPUs","created":"2022-02-17","cited_by_count":6},{"id":"1810.05486","title":"Training Deep Neural Network in Limited Precision","created":"2018-10-12","cited_by_count":3},{"id":"1812.04070","title":"SIMD-X: Programming and Processing of Graph Algorithms on GPUs","created":"2018-12-10","cited_by_count":2},{"id":"2201.08560","title":"Bit-GraphBLAS: Bit-Level Optimizations of Matrix-Centric Graph Processing on GPU","created":"2022-01-21","cited_by_count":2}],"next_cursor":null}