{"list":"other","total":60,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"2004.04906","title":"Dense Passage Retrieval for Open-Domain Question Answering","created":"2020-04-10","cited_by_count":3824},{"id":"1702.08734","title":"Billion-scale similarity search with GPUs","created":"2017-02-28","cited_by_count":2497},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"2002.08909","title":"REALM: Retrieval-Augmented Language Model Pre-Training","created":"2020-02-10","cited_by_count":2141},{"id":"1506.02626","title":"Learning both Weights and Connections for Efficient Neural Networks","created":"2015-06-08","cited_by_count":2031},{"id":"1611.09268","title":"MS MARCO: A Human Generated MAchine Reading COmprehension Dataset","created":"2016-11-28","cited_by_count":1605},{"id":"1608.08710","title":"Pruning Filters for Efficient ConvNets","created":"2016-08-31","cited_by_count":1143},{"id":"1603.09320","title":"Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs","created":"2016-03-30","cited_by_count":861},{"id":"2007.00808","title":"Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval","created":"2020-07-01","cited_by_count":849},{"id":"1606.07792","title":"Wide & Deep Learning for Recommender Systems","created":"2016-06-24","cited_by_count":747},{"id":"1902.08153","title":"Learned Step Size Quantization","created":"2019-02-21","cited_by_count":628},{"id":"1706.06978","title":"Deep Interest Network for Click-Through Rate Prediction","created":"2017-06-21","cited_by_count":544},{"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":"2010.08191","title":"RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answering","created":"2020-10-16","cited_by_count":413},{"id":"1708.05123","title":"Deep & Cross Network for Ad Click Predictions","created":"2017-08-17","cited_by_count":393},{"id":"1502.02551","title":"Deep Learning with Limited Numerical Precision","created":"2015-02-09","cited_by_count":376},{"id":"1906.00091","title":"Deep Learning Recommendation Model for Personalization and Recommendation Systems","created":"2019-05-31","cited_by_count":327},{"id":"2104.08253","title":"Condenser: a Pre-training Architecture for Dense Retrieval","created":"2021-04-16","cited_by_count":162},{"id":"1512.08571","title":"Structured Pruning of Deep Convolutional Neural Networks","created":"2015-12-29","cited_by_count":149},{"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},{"id":"1706.02379","title":"Training Quantized Nets: A Deeper Understanding","created":"2017-06-07","cited_by_count":75},{"id":"1909.02107","title":"Compositional Embeddings Using Complementary Partitions for Memory-Efficient Recommendation Systems","created":"2019-09-04","cited_by_count":68},{"id":"2003.05622","title":"Distributed Hierarchical GPU Parameter Server for Massive Scale Deep Learning Ads Systems","created":"2020-03-12","cited_by_count":60},{"id":"2101.11714","title":"TT-Rec: Tensor Train Compression for Deep Learning Recommendation Models","created":"2021-01-25","cited_by_count":58},{"id":"1709.03933","title":"Hash Embeddings for Efficient Word Representations","created":"2017-09-12","cited_by_count":55},{"id":"1710.00597","title":"DeepER -- Deep Entity Resolution","created":"2017-10-02","cited_by_count":54},{"id":"2009.05794","title":"Open Benchmarking for Click-Through Rate Prediction","created":"2020-09-12","cited_by_count":53},{"id":"2002.11252","title":"AutoEmb: Automated Embedding Dimensionality Search in Streaming Recommendations","created":"2020-02-26","cited_by_count":47},{"id":"2101.07577","title":"Learnable Embedding Sizes for Recommender Systems","created":"2021-01-19","cited_by_count":42},{"id":"2010.10784","title":"Learning to Embed Categorical Features without Embedding Tables for Recommendation","created":"2020-10-21","cited_by_count":38},{"id":"1908.09756","title":"Differentiable Product Quantization for End-to-End Embedding Compression","created":"2019-08-26","cited_by_count":36},{"id":"1711.01068","title":"Compressing Word Embeddings via Deep Compositional Code Learning","created":"2017-11-03","cited_by_count":35},{"id":"2007.14523","title":"Model Size Reduction Using Frequency Based Double Hashing for Recommender Systems","created":"2020-07-28","cited_by_count":33},{"id":"1806.06950","title":"GroupReduce: Block-Wise Low-Rank Approximation for Neural Language Model Shrinking","created":"2018-06-18","cited_by_count":32},{"id":"2204.09078","title":"AutoField: Automating Feature Selection in Deep Recommender Systems","created":"2022-04-19","cited_by_count":30},{"id":"2112.07221","title":"HET: Scaling out Huge Embedding Model Training via Cache-enabled Distributed Framework","created":"2021-12-14","cited_by_count":28},{"id":"2201.10095","title":"RecShard: Statistical Feature-Based Memory Optimization for Industry-Scale Neural Recommendation","created":"2022-01-25","cited_by_count":28},{"id":"2002.08530","title":"Learning Multi-granular Quantized Embeddings for Large-Vocab Categorical Features in Recommender Systems","created":"2020-02-20","cited_by_count":24},{"id":"1911.02079","title":"Post-Training 4-bit Quantization on Embedding Tables","created":"2019-11-05","cited_by_count":22},{"id":"2108.11333","title":"Lightweight Self-Attentive Sequential Recommendation","created":"2021-08-25","cited_by_count":22},{"id":"2210.08803","title":"Merlin HugeCTR: GPU-accelerated Recommender System Training and Inference","created":"2022-10-17","cited_by_count":20},{"id":"2106.02223","title":"Learning Elastic Embeddings for Customizing On-Device Recommenders","created":"2021-06-04","cited_by_count":19},{"id":"2206.13843","title":"Manu: A Cloud Native Vector Database Management System","created":"2022-06-28","cited_by_count":18},{"id":"2111.05897","title":"Persia: An Open, Hybrid System Scaling Deep Learning-based Recommenders up to 100 Trillion Parameters","created":"2021-11-10","cited_by_count":17},{"id":"2006.04466","title":"Differentiable Neural Input Search for Recommender Systems","created":"2020-06-08","cited_by_count":16},{"id":"2201.10442","title":"Serving Deep Learning Models with Deduplication from Relational Databases","created":"2022-01-25","cited_by_count":15},{"id":"2203.10135","title":"Learning Compressed Embeddings for On-Device Inference","created":"2022-03-18","cited_by_count":13},{"id":"2204.03281","title":"Single-shot Embedding Dimension Search in Recommender System","created":"2022-04-07","cited_by_count":13},{"id":"2003.07336","title":"Developing a Recommendation Benchmark for MLPerf Training and Inference","created":"2020-03-16","cited_by_count":12},{"id":"2108.11513","title":"Learning Effective and Efficient Embedding via an Adaptively-Masked Twins-based Layer","created":"2021-08-24","cited_by_count":12},{"id":"1806.09464","title":"Learning K-way D-dimensional Discrete Codes for Compact Embedding Representations","created":"2018-06-21","cited_by_count":11},{"id":"2109.02471","title":"Binary Code based Hash Embedding for Web-scale Applications","created":"2021-08-24","cited_by_count":11},{"id":"2302.01478","title":"Clustered Embedding Learning for Recommender Systems","created":"2023-02-03","cited_by_count":8},{"id":"2204.00281","title":"i-Razor: A Differentiable Neural Input Razor for Feature Selection and Dimension Search in DNN-Based Recommender Systems","created":"2022-04-01","cited_by_count":4}],"next_cursor":null}