{"list":"other","total":61,"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":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"1810.00826","title":"How Powerful are Graph Neural Networks?","created":"2018-10-01","cited_by_count":4393},{"id":"2004.04906","title":"Dense Passage Retrieval for Open-Domain Question Answering","created":"2020-04-10","cited_by_count":3824},{"id":"1704.01212","title":"Neural Message Passing for Quantum Chemistry","created":"2017-04-04","cited_by_count":3487},{"id":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"id":"2005.00687","title":"Open Graph Benchmark: Datasets for Machine Learning on Graphs","created":"2020-05-02","cited_by_count":2163},{"id":"1311.3618","title":"Describing Textures in the Wild","created":"2013-11-14","cited_by_count":2125},{"id":"1907.02893","title":"Invariant Risk Minimization","created":"2019-07-05","cited_by_count":1854},{"id":"1901.02860","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","created":"2019-01-09","cited_by_count":1850},{"id":"1805.01978","title":"Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination","created":"2018-05-05","cited_by_count":1845},{"id":"2007.14062","title":"Big Bird: Transformers for Longer Sequences","created":"2020-07-28","cited_by_count":1684},{"id":"2009.14794","title":"Rethinking Attention with Performers","created":"2020-09-30","cited_by_count":1601},{"id":"2010.13902","title":"Graph Contrastive Learning with Augmentations","created":"2020-10-22","cited_by_count":1208},{"id":"2007.01434","title":"In Search of Lost Domain Generalization","created":"2020-07-02","cited_by_count":1054},{"id":"2112.08654","title":"Learning to Prompt for Continual Learning","created":"2021-12-16","cited_by_count":944},{"id":"1911.00172","title":"Generalization through Memorization: Nearest Neighbor Language Models","created":"2019-11-01","cited_by_count":800},{"id":"2003.00688","title":"Out-of-Distribution Generalization via Risk Extrapolation (REx)","created":"2020-03-02","cited_by_count":742},{"id":"2007.08663","title":"TUDataset: A collection of benchmark datasets for learning with graphs","created":"2020-07-16","cited_by_count":728},{"id":"2103.10385","title":"GPT Understands, Too","created":"2021-03-18","cited_by_count":716},{"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":"2204.04799","title":"DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning","created":"2022-04-10","cited_by_count":642},{"id":"2006.05929","title":"Dataset Condensation with Gradient Matching","created":"2020-06-10","cited_by_count":516},{"id":"2203.11932","title":"Dataset Distillation by Matching Training Trajectories","created":"2022-03-22","cited_by_count":442},{"id":"2110.04181","title":"Dataset Condensation with Distribution Matching","created":"2021-10-08","cited_by_count":365},{"id":"2102.08259","title":"Dataset Condensation with Differentiable Siamese Augmentation","created":"2021-02-16","cited_by_count":291},{"id":"1703.00837","title":"Meta Networks","created":"2017-03-02","cited_by_count":269},{"id":"2203.08913","title":"Memorizing Transformers","created":"2022-03-16","cited_by_count":226},{"id":"2106.06607","title":"Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalization","created":"2021-06-11","cited_by_count":220},{"id":"2207.06881","title":"Recurrent Memory Transformer","created":"2022-07-14","cited_by_count":203},{"id":"2201.12872","title":"Discovering Invariant Rationales for Graph Neural Networks","created":"2022-01-30","cited_by_count":188},{"id":"1911.07979","title":"ASAP: Adaptive Structure Aware Pooling for Learning Hierarchical Graph Representations","created":"2019-11-18","cited_by_count":156},{"id":"2202.07179","title":"G-Mixup: Graph Data Augmentation for Graph Classification","created":"2022-02-15","cited_by_count":146},{"id":"2202.05441","title":"Learning Causally Invariant Representations for Out-of-Distribution Generalization on Graphs","created":"2022-02-11","cited_by_count":144},{"id":"2011.14027","title":"General Multi-label Image Classification with Transformers","created":"2020-11-27","cited_by_count":127},{"id":"2010.08853","title":"From Local Structures to Size Generalization in Graph Neural Networks","created":"2020-10-17","cited_by_count":124},{"id":"2106.02584","title":"Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning","created":"2021-06-04","cited_by_count":113},{"id":"2103.05045","title":"Size-Invariant Graph Representations for Graph Classification Extrapolations","created":"2021-03-08","cited_by_count":84},{"id":"2006.11527","title":"Memory Transformer","created":"2020-06-20","cited_by_count":76},{"id":"2105.05727","title":"BertGCN: Transductive Text Classification by Combining GCN and BERT","created":"2021-05-12","cited_by_count":74},{"id":"2003.05033","title":"Generalized Energy Based Models","created":"2020-03-10","cited_by_count":73},{"id":"2108.02958","title":"Learning Meta-class Memory for Few-Shot Semantic Segmentation","created":"2021-08-06","cited_by_count":56},{"id":"2004.12744","title":"Augmenting Transformers with KNN-Based Composite Memory for Dialogue","created":"2020-04-27","cited_by_count":53},{"id":"2011.08899","title":"Multimodal Prototypical Networks for Few-shot Learning","created":"2020-11-17","cited_by_count":48},{"id":"1709.03741","title":"Learning Graph-Level Representation for Drug Discovery","created":"2017-09-12","cited_by_count":43},{"id":"2010.08670","title":"CoDA: Contrast-enhanced and Diversity-promoting Data Augmentation for Natural Language Understanding","created":"2020-10-16","cited_by_count":41},{"id":"2006.03274","title":"GMAT: Global Memory Augmentation for Transformers","created":"2020-06-05","cited_by_count":36},{"id":"2210.16773","title":"An Efficient Memory-Augmented Transformer for Knowledge-Intensive NLP Tasks","created":"2022-10-30","cited_by_count":36},{"id":"1802.10542","title":"Memory-based Parameter Adaptation","created":"2018-02-28","cited_by_count":35},{"id":"2203.15243","title":"Fine-tuning Image Transformers using Learnable Memory","created":"2022-03-29","cited_by_count":34},{"id":"2009.10564","title":"GraphCrop: Subgraph Cropping for Graph Classification","created":"2020-09-22","cited_by_count":31},{"id":"2203.01522","title":"BatchFormer: Learning to Explore Sample Relationships for Robust Representation Learning","created":"2022-03-03","cited_by_count":29},{"id":"2110.08743","title":"GNN-LM: Language Modeling based on Global Contexts via GNN","created":"2021-10-17","cited_by_count":27},{"id":"2206.05314","title":"Large-Scale Retrieval for Reinforcement Learning","created":"2022-06-10","cited_by_count":24},{"id":"1805.08709","title":"A Simple Cache Model for Image Recognition","created":"2018-05-21","cited_by_count":20},{"id":"1906.08862","title":"Neural Stored-program Memory","created":"2019-05-25","cited_by_count":14},{"id":"2303.01421","title":"Learn to Memorize: Scalable Continual Learning in Semiparametric Models with Mixture-of-Neighbors Induction Memory","created":"2023-03-02","cited_by_count":12}],"next_cursor":null}