{"list":"other","total":52,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1710.10903","title":"Graph Attention Networks","created":"2017-10-30","cited_by_count":8923},{"id":"1706.02216","title":"Inductive Representation Learning on Large Graphs","created":"2017-06-07","cited_by_count":6320},{"id":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"1310.4546","title":"Distributed Representations of Words and Phrases and their Compositionality","created":"2013-10-16","cited_by_count":3474},{"id":"1710.10196","title":"Progressive Growing of GANs for Improved Quality, Stability, and Variation","created":"2017-10-27","cited_by_count":2988},{"id":"1906.08237","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","created":"2019-06-19","cited_by_count":2811},{"id":"1903.02428","title":"Fast Graph Representation Learning with PyTorch Geometric","created":"2019-03-06","cited_by_count":2434},{"id":"2005.00687","title":"Open Graph Benchmark: Datasets for Machine Learning on Graphs","created":"2020-05-02","cited_by_count":2163},{"id":"1902.07153","title":"Simplifying Graph Convolutional Networks","created":"2019-02-19","cited_by_count":1477},{"id":"1611.07308","title":"Variational Graph Auto-Encoders","created":"2016-11-21","cited_by_count":1382},{"id":"2010.13902","title":"Graph Contrastive Learning with Augmentations","created":"2020-10-22","cited_by_count":1208},{"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":"1905.12265","title":"Strategies for Pre-training Graph Neural Networks","created":"2019-05-29","cited_by_count":971},{"id":"2002.05287","title":"Geom-GCN: Geometric Graph Convolutional Networks","created":"2020-02-13","cited_by_count":826},{"id":"1906.00300","title":"Latent Retrieval for Weakly Supervised Open Domain Question Answering","created":"2019-06-01","cited_by_count":695},{"id":"1907.04931","title":"GraphSAINT: Graph Sampling Based Inductive Learning Method","created":"2019-07-10","cited_by_count":618},{"id":"2006.07988","title":"Adaptive Universal Generalized PageRank Graph Neural Network","created":"2020-06-14","cited_by_count":595},{"id":"1905.07953","title":"Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks","created":"2019-05-20","cited_by_count":541},{"id":"1704.03915","title":"Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution","created":"2017-04-12","cited_by_count":453},{"id":"1802.08773","title":"GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models","created":"2018-02-24","cited_by_count":413},{"id":"1809.05679","title":"Graph Convolutional Networks for Text Classification","created":"2018-09-15","cited_by_count":345},{"id":"2006.15437","title":"GPT-GNN: Generative Pre-Training of Graph Neural Networks","created":"2020-06-27","cited_by_count":303},{"id":"1901.09005","title":"Revisiting Self-Supervised Visual Representation Learning","created":"2019-01-25","cited_by_count":251},{"id":"2010.13993","title":"Combining Label Propagation and Simple Models Out-performs Graph Neural Networks","created":"2020-10-27","cited_by_count":202},{"id":"1905.01235","title":"Scaling and Benchmarking Self-Supervised Visual Representation Learning","created":"2019-05-03","cited_by_count":201},{"id":"2102.10757","title":"Self-Supervised Learning of Graph Neural Networks: A Unified Review","created":"2021-02-22","cited_by_count":184},{"id":"2001.05140","title":"Graph-Bert: Only Attention is Needed for Learning Graph Representations","created":"2020-01-15","cited_by_count":177},{"id":"2106.07476","title":"Training Graph Neural Networks with 1000 Layers","created":"2021-06-14","cited_by_count":169},{"id":"2002.03932","title":"Pre-training Tasks for Embedding-based Large-scale Retrieval","created":"2020-02-10","cited_by_count":153},{"id":"1807.09596","title":"Contextual Stochastic Block Models","created":"2018-07-23","cited_by_count":134},{"id":"1811.01727","title":"AttentionXML: Label Tree-based Attention-Aware Deep Model for High-Performance Extreme Multi-Label Text Classification","created":"2018-11-01","cited_by_count":102},{"id":"1901.08933","title":"Self-Supervised Generalisation with Meta Auxiliary Learning","created":"2019-01-25","cited_by_count":88},{"id":"2104.01404","title":"New Benchmarks for Learning on Non-Homophilous Graphs","created":"2021-04-03","cited_by_count":81},{"id":"2102.06966","title":"Graph Convolution for Semi-Supervised Classification: Improved Linear Separability and Out-of-Distribution Generalization","created":"2021-02-13","cited_by_count":70},{"id":"2110.00685","title":"Fast Multi-Resolution Transformer Fine-tuning for Extreme Multi-label Text Classification","created":"2021-10-01","cited_by_count":67},{"id":"2101.03305","title":"LightXML: Transformer with Dynamic Negative Sampling for High-Performance Extreme Multi-label Text Classification","created":"2021-01-09","cited_by_count":61},{"id":"1910.02356","title":"Text Level Graph Neural Network for Text Classification","created":"2019-10-06","cited_by_count":60},{"id":"1910.02370","title":"GraphZoom: A multi-level spectral approach for accurate and scalable graph embedding","created":"2019-10-06","cited_by_count":58},{"id":"2010.05878","title":"PECOS: Prediction for Enormous and Correlated Output Spaces","created":"2020-10-12","cited_by_count":50},{"id":"2001.05313","title":"Tensor Graph Convolutional Networks for Text Classification","created":"2020-01-12","cited_by_count":49},{"id":"1905.10881","title":"Optimizing Generalized PageRank Methods for Seed-Expansion Community Detection","created":"2019-05-26","cited_by_count":35},{"id":"2106.12657","title":"Extreme Multi-label Learning for Semantic Matching in Product Search","created":"2021-06-23","cited_by_count":28},{"id":"2007.02439","title":"Pretrained Generalized Autoregressive Model with Adaptive Probabilistic Label Clusters for Extreme Multi-label Text Classification","created":"2020-07-05","cited_by_count":25},{"id":"1708.04396","title":"BiRank: Towards Ranking on Bipartite Graphs","created":"2017-08-15","cited_by_count":15},{"id":"2106.12751","title":"Label Disentanglement in Partition-based Extreme Multilabel Classification","created":"2021-06-24","cited_by_count":7},{"id":"2004.00198","title":"Extreme Multi-label Classification from Aggregated Labels","created":"2020-04-01","cited_by_count":5},{"id":"2012.07654","title":"Session-Aware Query Auto-completion using Extreme Multi-label Ranking","created":"2020-12-09","cited_by_count":4},{"id":"2106.00730","title":"Enabling Efficiency-Precision Trade-offs for Label Trees in Extreme Classification","created":"2021-06-01","cited_by_count":2}],"next_cursor":null}