{"list":"other","total":66,"rows":[{"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":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1710.10903","title":"Graph Attention Networks","created":"2017-10-30","cited_by_count":8923},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1706.02216","title":"Inductive Representation Learning on Large Graphs","created":"2017-06-07","cited_by_count":6320},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1801.01290","title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","created":"2018-01-04","cited_by_count":4885},{"id":"1810.00826","title":"How Powerful are Graph Neural Networks?","created":"2018-10-01","cited_by_count":4393},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"1901.00596","title":"A Comprehensive Survey on Graph Neural Networks","created":"2019-01-03","cited_by_count":2919},{"id":"2107.13586","title":"Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing","created":"2021-07-28","cited_by_count":2234},{"id":"2005.00687","title":"Open Graph Benchmark: Datasets for Machine Learning on Graphs","created":"2020-05-02","cited_by_count":2163},{"id":"1509.06461","title":"Deep Reinforcement Learning with Double Q-learning","created":"2015-09-22","cited_by_count":1745},{"id":"1902.07153","title":"Simplifying Graph Convolutional Networks","created":"2019-02-19","cited_by_count":1477},{"id":"1809.10341","title":"Deep Graph Infomax","created":"2018-09-27","cited_by_count":1106},{"id":"1810.05997","title":"Predict then Propagate: Graph Neural Networks meet Personalized PageRank","created":"2018-10-14","cited_by_count":993},{"id":"1906.02629","title":"When Does Label Smoothing Help?","created":"2019-06-06","cited_by_count":988},{"id":"1911.12543","title":"How Can We Know What Language Models Know?","created":"2019-11-28","cited_by_count":959},{"id":"2007.02133","title":"Simple and Deep Graph Convolutional Networks","created":"2020-07-04","cited_by_count":860},{"id":"2002.05287","title":"Geom-GCN: Geometric Graph Convolutional Networks","created":"2020-02-13","cited_by_count":826},{"id":"1606.07947","title":"Sequence-Level Knowledge Distillation","created":"2016-06-25","cited_by_count":801},{"id":"2110.07602","title":"P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks","created":"2021-10-14","cited_by_count":689},{"id":"1907.10903","title":"DropEdge: Towards Deep Graph Convolutional Networks on Node Classification","created":"2019-07-25","cited_by_count":680},{"id":"2006.05582","title":"Contrastive Multi-View Representation Learning on Graphs","created":"2020-06-10","cited_by_count":652},{"id":"1801.10247","title":"FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling","created":"2018-01-30","cited_by_count":584},{"id":"1909.13021","title":"Multi-scale Attributed Node Embedding","created":"2019-09-28","cited_by_count":548},{"id":"1708.05866","title":"A Brief Survey of Deep Reinforcement Learning","created":"2017-08-19","cited_by_count":483},{"id":"1611.01838","title":"Entropy-SGD: Biasing Gradient Descent Into Wide Valleys","created":"2016-11-06","cited_by_count":359},{"id":"2006.09252","title":"Improving Graph Neural Network Expressivity via Subgraph Isomorphism Counting","created":"2020-06-16","cited_by_count":313},{"id":"1610.03295","title":"Safe, Multi-Agent, Reinforcement Learning for Autonomous Driving","created":"2016-10-11","cited_by_count":311},{"id":"2106.07178","title":"A Comprehensive Survey on Graph Anomaly Detection with Deep Learning","created":"2021-06-14","cited_by_count":230},{"id":"2005.11079","title":"Graph Random Neural Network for Semi-Supervised Learning on Graphs","created":"2020-05-22","cited_by_count":213},{"id":"1901.01343","title":"Graph Neural Networks with convolutional ARMA filters","created":"2019-01-05","cited_by_count":185},{"id":"2102.10757","title":"Self-Supervised Learning of Graph Neural Networks: A Unified Review","created":"2021-02-22","cited_by_count":184},{"id":"1809.05343","title":"Adaptive Sampling Towards Fast Graph Representation Learning","created":"2018-09-14","cited_by_count":180},{"id":"2110.08727","title":"Graph-less Neural Networks: Teaching Old MLPs New Tricks via Distillation","created":"2021-10-17","cited_by_count":152},{"id":"2003.10477","title":"Distilling Knowledge from Graph Convolutional Networks","created":"2020-03-23","cited_by_count":129},{"id":"2112.02472","title":"Augmentation-Free Self-Supervised Learning on Graphs","created":"2021-12-05","cited_by_count":94},{"id":"2106.03535","title":"Graph Neural Networks in Network Neuroscience","created":"2021-06-07","cited_by_count":92},{"id":"2005.14612","title":"Non-Local Graph Neural Networks","created":"2020-05-29","cited_by_count":91},{"id":"2009.10273","title":"Sub-graph Contrast for Scalable Self-Supervised Graph Representation Learning","created":"2020-09-22","cited_by_count":90},{"id":"2010.10046","title":"Line Graph Neural Networks for Link Prediction","created":"2020-10-20","cited_by_count":89},{"id":"2010.04925","title":"Regularizing Neural Networks via Adversarial Model Perturbation","created":"2020-10-10","cited_by_count":78},{"id":"2301.05792","title":"RMM: Reinforced Memory Management for Class-Incremental Learning","created":"2023-01-14","cited_by_count":66},{"id":"2012.06048","title":"Reinforced Multi-Teacher Selection for Knowledge Distillation","created":"2020-12-11","cited_by_count":63},{"id":"2111.04840","title":"Cold Brew: Distilling Graph Node Representations with Incomplete or Missing Neighborhoods","created":"2021-11-08","cited_by_count":58},{"id":"2110.04099","title":"Topology-Imbalance Learning for Semi-Supervised Node Classification","created":"2021-10-08","cited_by_count":56},{"id":"2006.15097","title":"Policy-GNN: Aggregation Optimization for Graph Neural Networks","created":"2020-06-26","cited_by_count":48},{"id":"1712.07465","title":"Recurrent Attentional Reinforcement Learning for Multi-label Image Recognition","created":"2017-12-20","cited_by_count":44},{"id":"2210.05801","title":"Linkless Link Prediction via Relational Distillation","created":"2022-10-11","cited_by_count":39},{"id":"1809.05884","title":"Multi-Label Image Classification via Knowledge Distillation from Weakly-Supervised Detection","created":"2018-09-16","cited_by_count":37},{"id":"1904.09482","title":"Improving Multi-Task Deep Neural Networks via Knowledge Distillation for Natural Language Understanding","created":"2019-04-20","cited_by_count":37},{"id":"2001.07620","title":"EdgeNets:Edge Varying Graph Neural Networks","created":"2020-01-21","cited_by_count":36},{"id":"1808.03405","title":"End-to-end Active Object Tracking and Its Real-world Deployment via Reinforcement Learning","created":"2018-08-10","cited_by_count":35},{"id":"2011.02255","title":"On Self-Distilling Graph Neural Network","created":"2020-11-04","cited_by_count":35},{"id":"2302.12449","title":"SGL-PT: A Strong Graph Learner with Graph Prompt Tuning","created":"2023-02-24","cited_by_count":35},{"id":"2107.11789","title":"ROD: Reception-aware Online Distillation for Sparse Graphs","created":"2021-07-25","cited_by_count":18},{"id":"2106.00241","title":"Reinforced Iterative Knowledge Distillation for Cross-Lingual Named Entity Recognition","created":"2021-06-01","cited_by_count":15},{"id":"2107.01908","title":"Reward-Adaptive Reinforcement Learning: Dynamic Policy Gradient Optimization for Bipedal Locomotion","created":"2021-07-05","cited_by_count":13},{"id":"2303.15015","title":"Towards Open Temporal Graph Neural Networks","created":"2023-03-27","cited_by_count":13},{"id":"2207.10839","title":"Robust Knowledge Adaptation for Dynamic Graph Neural Networks","created":"2022-07-22","cited_by_count":9},{"id":"2206.08088","title":"Reinforcement Learning-enhanced Shared-account Cross-domain Sequential Recommendation","created":"2022-06-16","cited_by_count":6},{"id":"2301.05163","title":"Signed Directed Graph Contrastive Learning with Laplacian Augmentation","created":"2023-01-12","cited_by_count":4},{"id":"2112.07934","title":"Graph Representation Learning via Contrasting Cluster Assignments","created":"2021-12-15","cited_by_count":2}],"next_cursor":null}