{"list":"other","total":52,"rows":[{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"1409.7495","title":"Unsupervised Domain Adaptation by Backpropagation","created":"2014-09-26","cited_by_count":1917},{"id":"1906.05849","title":"Contrastive Multiview Coding","created":"2019-06-13","cited_by_count":1301},{"id":"1808.06670","title":"Learning deep representations by mutual information estimation and maximization","created":"2018-08-20","cited_by_count":1273},{"id":"1906.00910","title":"Learning Representations by Maximizing Mutual Information Across Views","created":"2019-06-03","cited_by_count":734},{"id":"1801.04062","title":"MINE: Mutual Information Neural Estimation","created":"2018-01-12","cited_by_count":683},{"id":"1905.09272","title":"Data-Efficient Image Recognition with Contrastive Predictive Coding","created":"2019-05-22","cited_by_count":673},{"id":"1706.02515","title":"Self-Normalizing Neural Networks","created":"2017-06-08","cited_by_count":598},{"id":"1905.06922","title":"On Variational Bounds of Mutual Information","created":"2019-05-16","cited_by_count":559},{"id":"1902.09229","title":"A Theoretical Analysis of Contrastive Unsupervised Representation Learning","created":"2019-02-25","cited_by_count":530},{"id":"1606.00709","title":"f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization","created":"2016-06-02","cited_by_count":506},{"id":"1608.05745","title":"RETAIN: An Interpretable Predictive Model for Healthcare using Reverse Time Attention Mechanism","created":"2016-08-19","cited_by_count":349},{"id":"1907.13625","title":"On Mutual Information Maximization for Representation Learning","created":"2019-07-31","cited_by_count":316},{"id":"2106.04156","title":"Provable Guarantees for Self-Supervised Deep Learning with Spectral Contrastive Loss","created":"2021-06-08","cited_by_count":313},{"id":"2006.12013","title":"CLUB: A Contrastive Log-ratio Upper Bound of Mutual Information","created":"2020-06-22","cited_by_count":235},{"id":"2102.08850","title":"Contrastive Learning Inverts the Data Generating Process","created":"2021-02-17","cited_by_count":221},{"id":"1510.02192","title":"Simultaneous Deep Transfer Across Domains and Tasks","created":"2015-10-08","cited_by_count":206},{"id":"2002.04083","title":"Estimating Counterfactual Treatment Outcomes over Time Through Adversarially Balanced Representations","created":"2020-02-10","cited_by_count":155},{"id":"2008.10150","title":"Contrastive learning, multi-view redundancy, and linear models","created":"2020-08-24","cited_by_count":146},{"id":"2204.07258","title":"Causal Transformer for Estimating Counterfactual Outcomes","created":"2022-04-14","cited_by_count":123},{"id":"2006.06606","title":"What makes instance discrimination good for transfer learning?","created":"2020-06-11","cited_by_count":111},{"id":"2011.01625","title":"Causal Shapley Values: Exploiting Causal Knowledge to Explain Individual Predictions of Complex Models","created":"2020-11-03","cited_by_count":107},{"id":"1805.06826","title":"The Blessings of Multiple Causes","created":"2018-05-17","cited_by_count":104},{"id":"2202.14037","title":"Understanding Contrastive Learning Requires Incorporating Inductive Biases","created":"2022-02-28","cited_by_count":96},{"id":"1802.04537","title":"Tighter Variational Bounds are Not Necessarily Better","created":"2018-02-13","cited_by_count":76},{"id":"1902.00450","title":"Time Series Deconfounder: Estimating Treatment Effects over Time in the Presence of Hidden Confounders","created":"2019-02-01","cited_by_count":75},{"id":"2306.05268","title":"Factorized Contrastive Learning: Going Beyond Multi-view Redundancy","created":"2023-06-08","cited_by_count":75},{"id":"1806.04498","title":"The Unusual Effectiveness of Averaging in GAN Training","created":"2018-06-12","cited_by_count":73},{"id":"2304.09355","title":"To Compress or Not to Compress- Self-Supervised Learning and Information Theory: A Review","created":"2023-04-19","cited_by_count":72},{"id":"2303.09166","title":"Identifiability Results for Multimodal Contrastive Learning","created":"2023-03-16","cited_by_count":61},{"id":"2206.08311","title":"Continuous-Time Modeling of Counterfactual Outcomes Using Neural Controlled Differential Equations","created":"2022-06-16","cited_by_count":59},{"id":"2007.00163","title":"Identifying Causal-Effect Inference Failure with Uncertainty-Aware Models","created":"2020-07-01","cited_by_count":57},{"id":"2112.03493","title":"Conformal Sensitivity Analysis for Individual Treatment Effects","created":"2021-12-07","cited_by_count":40},{"id":"1710.05050","title":"Learning Independent Features with Adversarial Nets for Non-linear ICA","created":"2017-10-13","cited_by_count":33},{"id":"2208.09558","title":"Personalized Decision Making -- A Conceptual Introduction","created":"2022-08-19","cited_by_count":30},{"id":"1701.05132","title":"Estimation of causal effects with multiple treatments: a review and new ideas","created":"2017-01-18","cited_by_count":29},{"id":"2203.01228","title":"Estimating average causal effects from patient trajectories","created":"2022-03-02","cited_by_count":29},{"id":"2104.09323","title":"Sequential Deconfounding for Causal Inference with Unobserved Confounders","created":"2021-04-16","cited_by_count":24},{"id":"2202.11987","title":"Predicting the impact of treatments over time with uncertainty aware neural differential equations","created":"2022-02-24","cited_by_count":23},{"id":"2305.15742","title":"Counterfactual Generative Models for Time-Varying Treatments","created":"2023-05-25","cited_by_count":17},{"id":"2112.03013","title":"Deconfounding Temporal Autoencoder: Estimating Treatment Effects over Time Using Noisy Proxies","created":"2021-12-06","cited_by_count":16},{"id":"2306.11216","title":"CF-GODE: Continuous-Time Causal Inference for Multi-Agent Dynamical Systems","created":"2023-06-20","cited_by_count":16},{"id":"1805.08273","title":"Multiple Causal Inference with Latent Confounding","created":"2018-05-21","cited_by_count":14},{"id":"1708.04757","title":"Scalable Joint Models for Reliable Uncertainty-Aware Event Prediction","created":"2017-08-16","cited_by_count":13},{"id":"2311.04774","title":"Towards a Unified Framework of Contrastive Learning for Disentangled Representations","created":"2023-11-08","cited_by_count":13},{"id":"2102.11724","title":"Causal Mediation Analysis with Hidden Confounders","created":"2021-02-21","cited_by_count":10},{"id":"2402.06223","title":"Beyond DAGs: A Latent Partial Causal Model for Multimodal Learning","created":"2024-02-09","cited_by_count":10},{"id":"2112.03811","title":"Disentangled Counterfactual Recurrent Networks for Treatment Effect Inference over Time","created":"2021-12-07","cited_by_count":9},{"id":"2202.10885","title":"Learning Infomax and Domain-Independent Representations for Causal Effect Inference with Real-World Data","created":"2022-02-22","cited_by_count":9},{"id":"2302.09446","title":"Estimating Treatment Effects in Continuous Time with Hidden Confounders","created":"2023-02-19","cited_by_count":3}],"next_cursor":null}