{"list":"other","total":59,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"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":"1708.07747","title":"Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms","created":"2017-08-25","cited_by_count":4349},{"id":"1609.07843","title":"Pointer Sentinel Mixture Models","created":"2016-09-26","cited_by_count":3096},{"id":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"id":"1702.08734","title":"Billion-scale similarity search with GPUs","created":"2017-02-28","cited_by_count":2497},{"id":"1703.04730","title":"Understanding Black-box Predictions via Influence Functions","created":"2017-03-14","cited_by_count":1741},{"id":"2007.01434","title":"In Search of Lost Domain Generalization","created":"2020-07-02","cited_by_count":1054},{"id":"1710.03077","title":"Deeper, Broader and Artier Domain Generalization","created":"2017-10-09","cited_by_count":986},{"id":"1503.05671","title":"Optimizing Neural Networks with Kronecker-factored Approximate Curvature","created":"2015-03-19","cited_by_count":796},{"id":"1312.6211","title":"An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks","created":"2013-12-21","cited_by_count":722},{"id":"1904.02868","title":"Data Shapley: Equitable Valuation of Data for Machine Learning","created":"2019-04-05","cited_by_count":629},{"id":"2002.08484","title":"Estimating Training Data Influence by Tracing Gradient Descent","created":"2020-02-19","cited_by_count":580},{"id":"2402.04333","title":"LESS: Selecting Influential Data for Targeted Instruction Tuning","created":"2024-02-06","cited_by_count":532},{"id":"2008.03703","title":"What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimation","created":"2020-08-09","cited_by_count":497},{"id":"1806.10758","title":"A Benchmark for Interpretability Methods in Deep Neural Networks","created":"2018-06-28","cited_by_count":476},{"id":"1412.1193","title":"New insights and perspectives on the natural gradient method","created":"2014-12-03","cited_by_count":443},{"id":"1802.09568","title":"Shampoo: Preconditioned Stochastic Tensor Optimization","created":"2018-02-26","cited_by_count":426},{"id":"2303.14186","title":"TRAK: Attributing Model Behavior at Scale","created":"2023-03-24","cited_by_count":283},{"id":"1902.10275","title":"Towards Efficient Data Valuation Based on the Shapley Value","created":"2019-02-27","cited_by_count":281},{"id":"1508.07680","title":"Domain Generalization for Object Recognition with Multi-task Autoencoders","created":"2015-08-31","cited_by_count":253},{"id":"2006.14651","title":"Influence Functions in Deep Learning Are Fragile","created":"2020-06-25","cited_by_count":252},{"id":"2202.00622","title":"Datamodels: Predicting Predictions from Training Data","created":"2022-02-01","cited_by_count":189},{"id":"1811.09720","title":"Representer Point Selection for Explaining Deep Neural Networks","created":"2018-11-23","cited_by_count":187},{"id":"2110.14049","title":"Beta Shapley: a Unified and Noise-reduced Data Valuation Framework for Machine Learning","created":"2021-10-26","cited_by_count":165},{"id":"2112.12938","title":"Counterfactual Memorization in Neural Language Models","created":"2021-12-24","cited_by_count":156},{"id":"1806.03884","title":"Fast Approximate Natural Gradient Descent in a Kronecker-factored Eigenbasis","created":"2018-06-11","cited_by_count":146},{"id":"2005.06676","title":"Explaining Black Box Predictions and Unveiling Data Artifacts through Influence Functions","created":"2020-05-14","cited_by_count":144},{"id":"2209.05364","title":"If Influence Functions are the Answer, Then What is the Question?","created":"2022-09-12","cited_by_count":144},{"id":"1602.01407","title":"A Kronecker-factored approximate Fisher matrix for convolution layers","created":"2016-02-03","cited_by_count":141},{"id":"2212.04612","title":"Training Data Influence Analysis and Estimation: A Survey","created":"2022-12-09","cited_by_count":135},{"id":"2112.03052","title":"Scaling Up Influence Functions","created":"2021-12-06","cited_by_count":132},{"id":"2205.15466","title":"Data Banzhaf: A Robust Data Valuation Framework for Machine Learning","created":"2022-05-30","cited_by_count":132},{"id":"2310.00902","title":"DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models","created":"2023-10-02","cited_by_count":123},{"id":"2108.09331","title":"Influence Selection for Active Learning","created":"2021-08-20","cited_by_count":84},{"id":"2006.14026","title":"Subpopulation Data Poisoning Attacks","created":"2020-06-24","cited_by_count":70},{"id":"1906.08473","title":"Data Cleansing for Models Trained with SGD","created":"2019-06-20","cited_by_count":67},{"id":"2002.08025","title":"Influence Function based Data Poisoning Attacks to Top-N Recommender Systems","created":"2020-02-19","cited_by_count":63},{"id":"2303.08114","title":"Simfluence: Modeling the Influence of Individual Training Examples by Simulating Training Runs","created":"2023-03-14","cited_by_count":53},{"id":"2311.00636","title":"Kronecker-Factored Approximate Curvature for Modern Neural Network Architectures","created":"2023-11-01","cited_by_count":49},{"id":"1810.10118","title":"Interpreting Black Box Predictions using Fisher Kernels","created":"2018-10-23","cited_by_count":48},{"id":"2311.00500","title":"Intriguing Properties of Data Attribution on Diffusion Models","created":"2023-11-01","cited_by_count":47},{"id":"2312.06205","title":"The Journey, Not the Destination: How Data Guides Diffusion Models","created":"2023-12-11","cited_by_count":43},{"id":"2111.04683","title":"Revisiting Methods for Finding Influential Examples","created":"2021-11-08","cited_by_count":39},{"id":"2202.11844","title":"First is Better Than Last for Language Data Influence","created":"2022-02-24","cited_by_count":34},{"id":"2305.16971","title":"Theoretical and Practical Perspectives on what Influence Functions Do","created":"2023-05-26","cited_by_count":29},{"id":"2010.09030","title":"Explaining and Improving Model Behavior with k Nearest Neighbor Representations","created":"2020-10-18","cited_by_count":27},{"id":"2008.09624","title":"Optimization of Graph Neural Networks with Natural Gradient Descent","created":"2020-08-21","cited_by_count":26},{"id":"2201.12686","title":"Rank List Sensitivity of Recommender Systems to Interaction Perturbations","created":"2022-01-29","cited_by_count":20},{"id":"2303.12922","title":"Revisiting the Fragility of Influence Functions","created":"2023-03-22","cited_by_count":20},{"id":"2205.00359","title":"Adapting and Evaluating Influence-Estimation Methods for Gradient-Boosted Decision Trees","created":"2022-04-30","cited_by_count":16},{"id":"2310.19273","title":"The Memory Perturbation Equation: Understanding Model's Sensitivity to Data","created":"2023-10-30","cited_by_count":16},{"id":"2212.10722","title":"Contrastive Error Attribution for Finetuned Language Models","created":"2022-12-21","cited_by_count":12},{"id":"2305.19765","title":"A Bayesian Approach To Analysing Training Data Attribution In Deep Learning","created":"2023-05-31","cited_by_count":11},{"id":"2203.00089","title":"Amortized Proximal Optimization","created":"2022-02-28","cited_by_count":9},{"id":"2311.03386","title":"A Simple and Efficient Baseline for Data Attribution on Images","created":"2023-11-03","cited_by_count":5}],"next_cursor":null}