{"list":"other","total":55,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1603.02754","title":"XGBoost: A Scalable Tree Boosting System","created":"2016-03-09","cited_by_count":5166},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"id":"2004.05150","title":"Longformer: The Long-Document Transformer","created":"2020-04-10","cited_by_count":3413},{"id":"1510.00149","title":"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding","created":"2015-10-01","cited_by_count":2329},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"1506.02626","title":"Learning both Weights and Connections for Efficient Neural Networks","created":"2015-06-08","cited_by_count":2031},{"id":"2007.14062","title":"Big Bird: Transformers for Longer Sequences","created":"2020-07-28","cited_by_count":1684},{"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":"1609.08144","title":"Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation","created":"2016-09-26","cited_by_count":1475},{"id":"1608.08710","title":"Pruning Filters for Efficient ConvNets","created":"2016-08-31","cited_by_count":1143},{"id":"2106.11959","title":"Revisiting Deep Learning Models for Tabular Data","created":"2021-06-22","cited_by_count":740},{"id":"2207.01848","title":"TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second","created":"2022-07-05","cited_by_count":674},{"id":"1908.07442","title":"TabNet: Attentive Interpretable Tabular Learning","created":"2019-08-20","cited_by_count":648},{"id":"1706.02515","title":"Self-Normalizing Neural Networks","created":"2017-06-08","cited_by_count":598},{"id":"1511.00363","title":"BinaryConnect: Training Deep Neural Networks with binary weights during propagations","created":"2015-11-02","cited_by_count":592},{"id":"2106.03253","title":"Tabular Data: Deep Learning is Not All You Need","created":"2021-06-06","cited_by_count":535},{"id":"2102.00554","title":"Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networks","created":"2021-01-31","cited_by_count":527},{"id":"1512.02595","title":"Deep Speech 2: End-to-End Speech Recognition in English and Mandarin","created":"2015-12-08","cited_by_count":451},{"id":"1609.07061","title":"Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations","created":"2016-09-22","cited_by_count":426},{"id":"2012.06678","title":"TabTransformer: Tabular Data Modeling Using Contextual Embeddings","created":"2020-12-11","cited_by_count":409},{"id":"1810.11921","title":"AutoInt: Automatic Feature Interaction Learning via Self-Attentive Neural Networks","created":"2018-10-29","cited_by_count":320},{"id":"2106.01342","title":"SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Training","created":"2021-06-02","cited_by_count":319},{"id":"1906.01787","title":"Learning Deep Transformer Models for Machine Translation","created":"2019-06-05","cited_by_count":309},{"id":"1608.04493","title":"Dynamic Network Surgery for Efficient DNNs","created":"2016-08-16","cited_by_count":233},{"id":"2305.02997","title":"When Do Neural Nets Outperform Boosted Trees on Tabular Data?","created":"2023-05-04","cited_by_count":223},{"id":"2005.02359","title":"Classification-Based Anomaly Detection for General Data","created":"2020-05-05","cited_by_count":211},{"id":"1909.06312","title":"Neural Oblivious Decision Ensembles for Deep Learning on Tabular Data","created":"2019-09-13","cited_by_count":203},{"id":"2207.08815","title":"Why do tree-based models still outperform deep learning on tabular data?","created":"2022-07-18","cited_by_count":199},{"id":"2009.08576","title":"Pruning Neural Networks at Initialization: Why are We Missing the Mark?","created":"2020-09-18","cited_by_count":182},{"id":"1708.03731","title":"OpenML Benchmarking Suites","created":"2017-08-11","cited_by_count":178},{"id":"1602.02410","title":"Exploring the Limits of Language Modeling","created":"2016-02-07","cited_by_count":173},{"id":"2106.11189","title":"Well-tuned Simple Nets Excel on Tabular Datasets","created":"2021-06-21","cited_by_count":151},{"id":"2010.03633","title":"Simplicial Neural Networks","created":"2020-10-07","cited_by_count":110},{"id":"1905.00078","title":"Deep Learning for Audio Signal Processing","created":"2019-04-30","cited_by_count":92},{"id":"2003.01794","title":"Good Subnetworks Provably Exist: Pruning via Greedy Forward Selection","created":"2020-03-03","cited_by_count":70},{"id":"2006.09081","title":"Progressive Skeletonization: Trimming more fat from a network at initialization","created":"2020-06-16","cited_by_count":64},{"id":"2002.07772","title":"The Tree Ensemble Layer: Differentiability meets Conditional Computation","created":"2020-02-18","cited_by_count":57},{"id":"2011.03274","title":"Trust Issues: Uncertainty Estimation Does Not Enable Reliable OOD Detection On Medical Tabular Data","created":"2020-11-06","cited_by_count":52},{"id":"2002.07971","title":"Gradient Boosting Neural Networks: GrowNet","created":"2020-02-19","cited_by_count":46},{"id":"2207.03208","title":"Revisiting Pretraining Objectives for Tabular Deep Learning","created":"2022-07-07","cited_by_count":43},{"id":"2110.02585","title":"Simplicial Convolutional Neural Networks","created":"2021-10-06","cited_by_count":40},{"id":"2012.15330","title":"Sequential Deep Learning for Credit Risk Monitoring with Tabular Financial Data","created":"2020-12-30","cited_by_count":39},{"id":"1505.02445","title":"Network Filtering for Big Data: Triangulated Maximally Filtered Graph","created":"2015-05-10","cited_by_count":17},{"id":"2006.10598","title":"Neural Parameter Allocation Search","created":"2020-06-18","cited_by_count":15},{"id":"1602.07349","title":"Parsimonious modeling with Information Filtering Networks","created":"2016-02-23","cited_by_count":14},{"id":"1901.09124","title":"DeepSZ: A Novel Framework to Compress Deep Neural Networks by Using Error-Bounded Lossy Compression","created":"2019-01-26","cited_by_count":11},{"id":"2001.05934","title":"Simplicial complexes: higher-order spectral dimension and dynamics","created":"2020-01-16","cited_by_count":9},{"id":"2207.13914","title":"Anatomy of a Stablecoin's failure: the Terra-Luna case","created":"2022-07-28","cited_by_count":9},{"id":"2005.04692","title":"Topological regularization with information filtering networks","created":"2020-05-10","cited_by_count":6},{"id":"2306.15337","title":"Homological Neural Networks: A Sparse Architecture for Multivariate Complexity","created":"2023-06-27","cited_by_count":5},{"id":"2012.06260","title":"Comparison of Anomaly Detectors: Context Matters","created":"2020-12-11","cited_by_count":2}],"next_cursor":null}