{"list":"other","total":52,"rows":[{"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":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1706.02216","title":"Inductive Representation Learning on Large Graphs","created":"2017-06-07","cited_by_count":6320},{"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":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"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":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"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":"1603.08511","title":"Colorful Image Colorization","created":"2016-03-28","cited_by_count":1114},{"id":"1809.10341","title":"Deep Graph Infomax","created":"2018-09-27","cited_by_count":1106},{"id":"1703.00564","title":"MoleculeNet: A Benchmark for Molecular Machine Learning","created":"2017-03-02","cited_by_count":1051},{"id":"1905.12265","title":"Strategies for Pre-training Graph Neural Networks","created":"2019-05-29","cited_by_count":971},{"id":"2001.07676","title":"Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference","created":"2020-01-21","cited_by_count":938},{"id":"1810.02244","title":"Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks","created":"2018-10-04","cited_by_count":881},{"id":"2202.10054","title":"Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution","created":"2022-02-21","cited_by_count":739},{"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":"2009.07118","title":"It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners","created":"2020-09-15","cited_by_count":669},{"id":"2003.08271","title":"Pre-trained Models for Natural Language Processing: A Survey","created":"2020-03-18","cited_by_count":505},{"id":"2006.09963","title":"GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training","created":"2020-06-17","cited_by_count":463},{"id":"1908.01000","title":"InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization","created":"2019-07-31","cited_by_count":441},{"id":"1911.05485","title":"Diffusion Improves Graph Learning","created":"2019-10-28","cited_by_count":414},{"id":"2006.15437","title":"GPT-GNN: Generative Pre-Training of Graph Neural Networks","created":"2020-06-27","cited_by_count":303},{"id":"2103.00111","title":"Graph Self-Supervised Learning: A Survey","created":"2021-02-27","cited_by_count":289},{"id":"2106.07594","title":"Graph Contrastive Learning Automated","created":"2021-06-10","cited_by_count":287},{"id":"2203.17274","title":"Exploring Visual Prompts for Adapting Large-Scale Models","created":"2022-03-31","cited_by_count":274},{"id":"2002.09434","title":"Few-Shot Learning via Learning the Representation, Provably","created":"2020-02-21","cited_by_count":214},{"id":"2106.05819","title":"Adversarial Graph Augmentation to Improve Graph Contrastive Learning","created":"2021-06-10","cited_by_count":200},{"id":"2006.11650","title":"On the Theory of Transfer Learning: The Importance of Task Diversity","created":"2020-06-20","cited_by_count":186},{"id":"2203.06904","title":"Delta Tuning: A Comprehensive Study of Parameter Efficient Methods for Pre-trained Language Models","created":"2022-03-14","cited_by_count":180},{"id":"2202.03104","title":"SimGRACE: A Simple Framework for Graph Contrastive Learning without Data Augmentation","created":"2022-02-07","cited_by_count":171},{"id":"1905.02850","title":"Understanding Attention and Generalization in Graph Neural Networks","created":"2019-05-08","cited_by_count":169},{"id":"2110.00987","title":"Motif-based Graph Self-Supervised Learning for Molecular Property Prediction","created":"2021-10-03","cited_by_count":159},{"id":"2110.03753","title":"From Stars to Subgraphs: Uplifting Any GNN with Local Structure Awareness","created":"2021-10-07","cited_by_count":155},{"id":"2110.02910","title":"Equivariant Subgraph Aggregation Networks","created":"2021-10-06","cited_by_count":154},{"id":"2110.13197","title":"Nested Graph Neural Networks","created":"2021-10-25","cited_by_count":137},{"id":"2106.04113","title":"Self-supervised Graph-level Representation Learning with Local and Global Structure","created":"2021-06-08","cited_by_count":125},{"id":"2010.08853","title":"From Local Structures to Size Generalization in Graph Neural Networks","created":"2020-10-17","cited_by_count":124},{"id":"2005.00944","title":"Understanding and Improving Information Transfer in Multi-Task Learning","created":"2020-05-02","cited_by_count":114},{"id":"2206.11140","title":"Understanding and Extending Subgraph GNNs by Rethinking Their Symmetries","created":"2022-06-22","cited_by_count":112},{"id":"2006.10141","title":"Self-supervised Learning on Graphs: Deep Insights and New Direction","created":"2020-06-17","cited_by_count":108},{"id":"2012.06002","title":"Overcoming Catastrophic Forgetting in Graph Neural Networks","created":"2020-12-10","cited_by_count":95},{"id":"2106.09226","title":"Why Do Pretrained Language Models Help in Downstream Tasks? An Analysis of Head and Prompt Tuning","created":"2021-06-17","cited_by_count":82},{"id":"2010.11418","title":"Rethinking pooling in graph neural networks","created":"2020-10-22","cited_by_count":73},{"id":"2110.00577","title":"Reconstruction for Powerful Graph Representations","created":"2021-10-01","cited_by_count":65},{"id":"2204.07356","title":"Vision-and-Language Pretrained Models: A Survey","created":"2022-04-15","cited_by_count":50},{"id":"2104.08682","title":"Rethinking Network Pruning -- under the Pre-train and Fine-tune Paradigm","created":"2021-04-18","cited_by_count":40},{"id":"2201.01702","title":"Bringing Your Own View: Graph Contrastive Learning without Prefabricated Data Augmentations","created":"2022-01-04","cited_by_count":28},{"id":"2202.07893","title":"A Survey of Pretraining on Graphs: Taxonomy, Methods, and Applications","created":"2022-02-16","cited_by_count":23},{"id":"1805.02411","title":"Prioritizing network communities","created":"2018-05-07","cited_by_count":14}],"next_cursor":null}