{"list":"other","total":53,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"1810.00826","title":"How Powerful are Graph Neural Networks?","created":"2018-10-01","cited_by_count":4393},{"id":"2005.00687","title":"Open Graph Benchmark: Datasets for Machine Learning on Graphs","created":"2020-05-02","cited_by_count":2163},{"id":"2001.06782","title":"Gradient Surgery for Multi-Task Learning","created":"2020-01-19","cited_by_count":1256},{"id":"2010.13902","title":"Graph Contrastive Learning with Augmentations","created":"2020-10-22","cited_by_count":1208},{"id":"1611.00712","title":"The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables","created":"2016-11-02","cited_by_count":1148},{"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":"1811.05868","title":"Pitfalls of Graph Neural Network Evaluation","created":"2018-11-14","cited_by_count":1007},{"id":"1603.08861","title":"Revisiting Semi-Supervised Learning with Graph Embeddings","created":"2016-03-29","cited_by_count":976},{"id":"1905.12265","title":"Strategies for Pre-training Graph Neural Networks","created":"2019-05-29","cited_by_count":971},{"id":"2006.05582","title":"Contrastive Multi-View Representation Learning on Graphs","created":"2020-06-10","cited_by_count":652},{"id":"1804.08328","title":"Taskonomy: Disentangling Task Transfer Learning","created":"2018-04-23","cited_by_count":634},{"id":"2006.04131","title":"Deep Graph Contrastive Representation Learning","created":"2020-06-07","cited_by_count":539},{"id":"2010.14945","title":"Graph Contrastive Learning with Adaptive Augmentation","created":"2020-10-27","cited_by_count":519},{"id":"2110.14048","title":"Conflict-Averse Gradient Descent for Multi-task Learning","created":"2021-10-26","cited_by_count":459},{"id":"2205.10803","title":"GraphMAE: Self-Supervised Masked Graph Autoencoders","created":"2022-05-22","cited_by_count":448},{"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":"2205.14865","title":"Prompt-aligned Gradient for Prompt Tuning","created":"2022-05-30","cited_by_count":341},{"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":"1902.08412","title":"Adversarial Attacks on Graph Neural Networks via Meta Learning","created":"2019-02-22","cited_by_count":261},{"id":"2110.07728","title":"Pre-training Molecular Graph Representation with 3D Geometry","created":"2021-10-07","cited_by_count":248},{"id":"2006.05531","title":"GEOM: Energy-annotated molecular conformations for property prediction and molecular generation","created":"2020-06-09","cited_by_count":243},{"id":"1708.07860","title":"Multi-task Self-Supervised Visual Learning","created":"2017-08-25","cited_by_count":200},{"id":"2106.05819","title":"Adversarial Graph Augmentation to Improve Graph Contrastive Learning","created":"2021-06-10","cited_by_count":200},{"id":"2102.10757","title":"Self-Supervised Learning of Graph Neural Networks: A Unified Review","created":"2021-02-22","cited_by_count":184},{"id":"2202.03104","title":"SimGRACE: A Simple Framework for Graph Contrastive Learning without Data Augmentation","created":"2022-02-07","cited_by_count":171},{"id":"2110.08727","title":"Graph-less Neural Networks: Teaching Old MLPs New Tricks via Distillation","created":"2021-10-17","cited_by_count":152},{"id":"2105.07342","title":"Self-supervised Learning on Graphs: Contrastive, Generative,or Predictive","created":"2021-05-16","cited_by_count":136},{"id":"2106.04113","title":"Self-supervised Graph-level Representation Learning with Local and Global Structure","created":"2021-06-08","cited_by_count":125},{"id":"2006.09136","title":"When Does Self-Supervision Help Graph Convolutional Networks?","created":"2020-06-16","cited_by_count":121},{"id":"2005.00944","title":"Understanding and Improving Information Transfer in Multi-Task Learning","created":"2020-05-02","cited_by_count":114},{"id":"2006.10141","title":"Self-supervised Learning on Graphs: Deep Insights and New Direction","created":"2020-06-17","cited_by_count":108},{"id":"2203.00759","title":"HyperPrompt: Prompt-based Task-Conditioning of Transformers","created":"2022-03-01","cited_by_count":67},{"id":"2206.07869","title":"Let Invariant Rationale Discovery Inspire Graph Contrastive Learning","created":"2022-06-16","cited_by_count":57},{"id":"1711.09082","title":"Cross-Domain Self-supervised Multi-task Feature Learning using Synthetic Imagery","created":"2017-11-24","cited_by_count":56},{"id":"2106.05470","title":"Automated Self-Supervised Learning for Graphs","created":"2021-06-10","cited_by_count":50},{"id":"2009.07111","title":"Contrastive and Generative Graph Convolutional Networks for Graph-based Semi-Supervised Learning","created":"2020-09-15","cited_by_count":43},{"id":"2003.01604","title":"Self-Supervised Graph Representation Learning via Global Context Prediction","created":"2020-03-03","cited_by_count":38},{"id":"2210.02016","title":"Multi-task Self-supervised Graph Neural Networks Enable Stronger Task Generalization","created":"2022-10-05","cited_by_count":35},{"id":"2107.08765","title":"Adaptive Transfer Learning on Graph Neural Networks","created":"2021-07-19","cited_by_count":31},{"id":"2306.05628","title":"Quantifying the Knowledge in GNNs for Reliable Distillation into MLPs","created":"2023-06-09","cited_by_count":25},{"id":"2305.10758","title":"Extracting Low-/High- Frequency Knowledge from Graph Neural Networks and Injecting it into MLPs: An Effective GNN-to-MLP Distillation Framework","created":"2023-05-18","cited_by_count":24},{"id":"2010.12609","title":"Iterative Graph Self-Distillation","created":"2020-10-23","cited_by_count":21},{"id":"2103.08862","title":"Gumbel-Attention for Multi-modal Machine Translation","created":"2021-03-16","cited_by_count":20},{"id":"2106.08541","title":"Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages","created":"2021-06-16","cited_by_count":11},{"id":"2210.02097","title":"Teaching Yourself: Graph Self-Distillation on Neighborhood for Node Classification","created":"2022-10-05","cited_by_count":6},{"id":"2210.02099","title":"Automated Graph Self-supervised Learning via Multi-teacher Knowledge Distillation","created":"2022-10-05","cited_by_count":6}],"next_cursor":null}