{"list":"other","total":81,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"1705.07874","title":"A Unified Approach to Interpreting Model Predictions","created":"2017-05-22","cited_by_count":6555},{"id":"1312.6199","title":"Intriguing properties of neural networks","created":"2013-12-21","cited_by_count":5155},{"id":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"id":"1703.01365","title":"Axiomatic Attribution for Deep Networks","created":"2017-03-04","cited_by_count":3384},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691},{"id":"1311.2901","title":"Visualizing and Understanding Convolutional Networks","created":"2013-11-12","cited_by_count":2290},{"id":"2012.07436","title":"Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting","created":"2020-12-14","cited_by_count":2169},{"id":"1308.3432","title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation","created":"2013-08-15","cited_by_count":2079},{"id":"2004.07780","title":"Shortcut Learning in Deep Neural Networks","created":"2020-04-16","cited_by_count":1969},{"id":"1702.08608","title":"Towards A Rigorous Science of Interpretable Machine Learning","created":"2017-02-28","cited_by_count":1416},{"id":"1810.03292","title":"Sanity Checks for Saliency Maps","created":"2018-10-08","cited_by_count":1156},{"id":"1611.00712","title":"The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables","created":"2016-11-02","cited_by_count":1148},{"id":"2007.04612","title":"Concept Bottleneck Models","created":"2020-07-09","cited_by_count":1032},{"id":"2102.12452","title":"Probing Classifiers: Promises, Shortcomings, and Advances","created":"2021-02-24","cited_by_count":876},{"id":"1806.07421","title":"RISE: Randomized Input Sampling for Explanation of Black-box Models","created":"2018-06-19","cited_by_count":838},{"id":"2002.12327","title":"A Primer in BERTology: What we know about how BERT works","created":"2020-02-27","cited_by_count":815},{"id":"2005.00928","title":"Quantifying Attention Flow in Transformers","created":"2020-05-02","cited_by_count":775},{"id":"2212.03827","title":"Discovering Latent Knowledge in Language Models Without Supervision","created":"2022-12-07","cited_by_count":767},{"id":"1912.09363","title":"Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting","created":"2019-12-19","cited_by_count":761},{"id":"1905.10437","title":"N-BEATS: Neural basis expansion analysis for interpretable time series forecasting","created":"2019-05-24","cited_by_count":753},{"id":"1806.10574","title":"This Looks Like That: Deep Learning for Interpretable Image Recognition","created":"2018-06-27","cited_by_count":737},{"id":"1903.03894","title":"GNNExplainer: Generating Explanations for Graph Neural Networks","created":"2019-03-10","cited_by_count":737},{"id":"2104.08696","title":"Knowledge Neurons in Pretrained Transformers","created":"2021-04-18","cited_by_count":601},{"id":"2009.07896","title":"Captum: A unified and generic model interpretability library for PyTorch","created":"2020-09-16","cited_by_count":547},{"id":"1904.12584","title":"The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision","created":"2019-04-26","cited_by_count":372},{"id":"1904.06627","title":"Multi-Similarity Loss with General Pair Weighting for Deep Metric Learning","created":"2019-04-14","cited_by_count":368},{"id":"1711.00867","title":"The (Un)reliability of saliency methods","created":"2017-11-02","cited_by_count":333},{"id":"2004.13912","title":"Neural Additive Models: Interpretable Machine Learning with Neural Nets","created":"2020-04-29","cited_by_count":319},{"id":"2205.15480","title":"Post-hoc Concept Bottleneck Models","created":"2022-05-31","cited_by_count":293},{"id":"1906.05714","title":"A Multiscale Visualization of Attention in the Transformer Model","created":"2019-06-12","cited_by_count":292},{"id":"1606.04155","title":"Rationalizing Neural Predictions","created":"2016-06-13","cited_by_count":281},{"id":"1910.08485","title":"Understanding Deep Networks via Extremal Perturbations and Smooth Masks","created":"2019-10-18","cited_by_count":259},{"id":"2206.08496","title":"Self-Supervised Contrastive Pre-Training For Time Series via Time-Frequency Consistency","created":"2022-06-17","cited_by_count":250},{"id":"1903.05662","title":"Understanding Straight-Through Estimator in Training Activation Quantized Neural Nets","created":"2019-03-13","cited_by_count":231},{"id":"2010.00711","title":"A Survey of the State of Explainable AI for Natural Language Processing","created":"2020-10-01","cited_by_count":206},{"id":"2201.12987","title":"Interpretable and Generalizable Graph Learning via Stochastic Attention Mechanism","created":"2022-01-31","cited_by_count":171},{"id":"2108.04840","title":"Post-hoc Interpretability for Neural NLP: A Survey","created":"2021-08-10","cited_by_count":156},{"id":"1904.07846","title":"Temporal Cycle-Consistency Learning","created":"2019-04-16","cited_by_count":154},{"id":"2203.14001","title":"Knowledge Distillation with the Reused Teacher Classifier","created":"2022-03-26","cited_by_count":141},{"id":"2102.13076","title":"Benchmarking and Survey of Explanation Methods for Black Box Models","created":"2021-02-25","cited_by_count":136},{"id":"2205.14459","title":"CyCLIP: Cyclic Contrastive Language-Image Pretraining","created":"2022-05-28","cited_by_count":127},{"id":"1905.08160","title":"Interpretable Neural Predictions with Differentiable Binary Variables","created":"2019-05-20","cited_by_count":126},{"id":"2206.11104","title":"OpenXAI: Towards a Transparent Evaluation of Model Explanations","created":"2022-06-22","cited_by_count":126},{"id":"2110.10790","title":"Human-Centered Explainable AI (XAI): From Algorithms to User Experiences","created":"2021-10-20","cited_by_count":123},{"id":"2110.05357","title":"Graph-Guided Network for Irregularly Sampled Multivariate Time Series","created":"2021-10-11","cited_by_count":111},{"id":"2010.13924","title":"Benchmarking Deep Learning Interpretability in Time Series Predictions","created":"2020-10-26","cited_by_count":102},{"id":"2106.00786","title":"The Out-of-Distribution Problem in Explainability and Search Methods for Feature Importance Explanations","created":"2021-06-01","cited_by_count":87},{"id":"2208.09339","title":"Evaluating Explainability for Graph Neural Networks","created":"2022-08-19","cited_by_count":87},{"id":"2012.00073","title":"TimeSHAP: Explaining Recurrent Models through Sequence Perturbations","created":"2020-11-30","cited_by_count":74},{"id":"2106.05303","title":"Explaining Time Series Predictions with Dynamic Masks","created":"2021-06-09","cited_by_count":73},{"id":"2104.00950","title":"Explainable Artificial Intelligence (XAI) on TimeSeries Data: A Survey","created":"2021-04-02","cited_by_count":72},{"id":"2111.14338","title":"Improving Deep Learning Interpretability by Saliency Guided Training","created":"2021-11-29","cited_by_count":68},{"id":"1909.07082","title":"Towards a Rigorous Evaluation of XAI Methods on Time Series","created":"2019-09-16","cited_by_count":67},{"id":"2202.00734","title":"Framework for Evaluating Faithfulness of Local Explanations","created":"2022-02-01","cited_by_count":55},{"id":"2006.00442","title":"Evaluations and Methods for Explanation through Robustness Analysis","created":"2020-05-31","cited_by_count":51},{"id":"2107.11400","title":"Robust Explainability: A Tutorial on Gradient-Based Attribution Methods for Deep Neural Networks","created":"2021-07-23","cited_by_count":48},{"id":"1706.08838","title":"TimeNet: Pre-trained deep recurrent neural network for time series classification","created":"2017-06-23","cited_by_count":46},{"id":"2106.09078","title":"Probing GNN Explainers: A Rigorous Theoretical and Empirical Analysis of GNN Explanation Methods","created":"2021-06-16","cited_by_count":36},{"id":"2210.08151","title":"ProtoVAE: A Trustworthy Self-Explainable Prototypical Variational Model","created":"2022-10-15","cited_by_count":34},{"id":"2107.14317","title":"Temporal Dependencies in Feature Importance for Time Series Predictions","created":"2021-07-29","cited_by_count":27},{"id":"2210.16966","title":"Interpretable Geometric Deep Learning via Learnable Randomness Injection","created":"2022-10-30","cited_by_count":27},{"id":"2105.04854","title":"Improving Molecular Graph Neural Network Explainability with Orthonormalization and Induced Sparsity","created":"2021-05-11","cited_by_count":20},{"id":"2303.02794","title":"CoRTX: Contrastive Framework for Real-time Explanation","created":"2023-03-05","cited_by_count":20},{"id":"2110.00527","title":"Consistent Explanations by Contrastive Learning","created":"2021-10-01","cited_by_count":18},{"id":"2206.15049","title":"ZeroC: A Neuro-Symbolic Model for Zero-shot Concept Recognition and Acquisition at Inference Time","created":"2022-06-30","cited_by_count":16},{"id":"2209.15246","title":"Your Out-of-Distribution Detection Method is Not Robust!","created":"2022-09-30","cited_by_count":16},{"id":"2109.09426","title":"A Meta-Learning Approach for Training Explainable Graph Neural Networks","created":"2021-09-20","cited_by_count":15},{"id":"2012.12368","title":"Understanding and Increasing Efficiency of Frank-Wolfe Adversarial Training","created":"2020-12-22","cited_by_count":14},{"id":"2107.14000","title":"Resisting Out-of-Distribution Data Problem in Perturbation of XAI","created":"2021-07-27","cited_by_count":12},{"id":"2112.01020","title":"Learning Optimal Predictive Checklists","created":"2021-12-02","cited_by_count":10},{"id":"2007.07606","title":"timeXplain -- A Framework for Explaining the Predictions of Time Series Classifiers","created":"2020-07-15","cited_by_count":9},{"id":"2006.13561","title":"Differentiable Window for Dynamic Local Attention","created":"2020-06-24","cited_by_count":8},{"id":"1910.02176","title":"Straight-Through Estimator as Projected Wasserstein Gradient Flow","created":"2019-10-05","cited_by_count":7},{"id":"2210.05411","title":"Class-Specific Explainability for Deep Time Series Classifiers","created":"2022-10-11","cited_by_count":6},{"id":"2012.01145","title":"Ultrasound Diagnosis of COVID-19: Robustness and Explainability","created":"2020-11-30","cited_by_count":1}],"next_cursor":null}