{"list":"other","total":63,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"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":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"2005.00687","title":"Open Graph Benchmark: Datasets for Machine Learning on Graphs","created":"2020-05-02","cited_by_count":2163},{"id":"2002.05287","title":"Geom-GCN: Geometric Graph Convolutional Networks","created":"2020-02-13","cited_by_count":826},{"id":"1811.03962","title":"A Convergence Theory for Deep Learning via Over-Parameterization","created":"2018-11-09","cited_by_count":787},{"id":"2205.12454","title":"Recipe for a General, Powerful, Scalable Graph Transformer","created":"2022-05-25","cited_by_count":713},{"id":"2006.07988","title":"Adaptive Universal Generalized PageRank Graph Neural Network","created":"2020-06-14","cited_by_count":595},{"id":"2003.01332","title":"Heterogeneous Graph Transformer","created":"2020-03-03","cited_by_count":582},{"id":"1901.08584","title":"Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks","created":"2019-01-24","cited_by_count":566},{"id":"2106.03893","title":"Rethinking Graph Transformers with Spectral Attention","created":"2021-06-07","cited_by_count":473},{"id":"1811.04918","title":"Learning and Generalization in Overparameterized Neural Networks, Going Beyond Two Layers","created":"2018-11-12","cited_by_count":340},{"id":"2006.15437","title":"GPT-GNN: Generative Pre-Training of Graph Neural Networks","created":"2020-06-27","cited_by_count":303},{"id":"2012.09816","title":"Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning","created":"2020-12-17","cited_by_count":297},{"id":"2206.08164","title":"Long Range Graph Benchmark","created":"2022-06-16","cited_by_count":263},{"id":"1905.09550","title":"Revisiting Graph Neural Networks: All We Have is Low-Pass Filters","created":"2019-05-23","cited_by_count":261},{"id":"1905.13210","title":"Generalization Bounds of Stochastic Gradient Descent for Wide and Deep Neural Networks","created":"2019-05-30","cited_by_count":222},{"id":"2002.06157","title":"Generalization and Representational Limits of Graph Neural Networks","created":"2020-02-14","cited_by_count":218},{"id":"2306.08385","title":"NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classification","created":"2023-06-14","cited_by_count":210},{"id":"2201.08821","title":"Representing Long-Range Context for Graph Neural Networks with Global Attention","created":"2022-01-21","cited_by_count":195},{"id":"2202.03036","title":"Structure-Aware Transformer for Graph Representation Learning","created":"2022-02-07","cited_by_count":194},{"id":"2001.05140","title":"Graph-Bert: Only Attention is Needed for Learning Graph Representations","created":"2020-01-15","cited_by_count":177},{"id":"1905.13192","title":"Graph Neural Tangent Kernel: Fusing Graph Neural Networks with Graph Kernels","created":"2019-05-30","cited_by_count":161},{"id":"2206.04910","title":"NAGphormer: A Tokenized Graph Transformer for Node Classification in Large Graphs","created":"2022-06-10","cited_by_count":137},{"id":"1905.06874","title":"Behavior Sequence Transformer for E-commerce Recommendation in Alibaba","created":"2019-05-15","cited_by_count":130},{"id":"1906.04688","title":"An Improved Analysis of Training Over-parameterized Deep Neural Networks","created":"2019-06-11","cited_by_count":121},{"id":"2105.15134","title":"Toward Understanding the Feature Learning Process of Self-supervised Contrastive Learning","created":"2021-05-31","cited_by_count":119},{"id":"2301.09505","title":"Rethinking the Expressive Power of GNNs via Graph Biconnectivity","created":"2023-01-23","cited_by_count":119},{"id":"2108.03348","title":"Global Self-Attention as a Replacement for Graph Convolution","created":"2021-08-07","cited_by_count":114},{"id":"2005.10190","title":"Feature Purification: How Adversarial Training Performs Robust Deep Learning","created":"2020-05-20","cited_by_count":107},{"id":"2305.16380","title":"Scan and Snap: Understanding Training Dynamics and Token Composition in 1-layer Transformer","created":"2023-05-25","cited_by_count":102},{"id":"1706.03175","title":"Recovery Guarantees for One-hidden-layer Neural Networks","created":"2017-06-10","cited_by_count":94},{"id":"2210.09221","title":"Vision Transformers provably learn spatial structure","created":"2022-10-13","cited_by_count":93},{"id":"2303.04245","title":"How Do Transformers Learn Topic Structure: Towards a Mechanistic Understanding","created":"2023-03-07","cited_by_count":86},{"id":"2012.07690","title":"A PAC-Bayesian Approach to Generalization Bounds for Graph Neural Networks","created":"2020-12-14","cited_by_count":85},{"id":"1905.01004","title":"Stability and Generalization of Graph Convolutional Neural Networks","created":"2019-05-03","cited_by_count":81},{"id":"2302.06015","title":"A Theoretical Understanding of Shallow Vision Transformers: Learning, Generalization, and Sample Complexity","created":"2023-02-12","cited_by_count":77},{"id":"2210.03930","title":"Hierarchical Graph Transformer with Adaptive Node Sampling","created":"2022-10-08","cited_by_count":72},{"id":"2110.13094","title":"Gophormer: Ego-Graph Transformer for Node Classification","created":"2021-10-25","cited_by_count":63},{"id":"2202.00645","title":"Generalization Analysis of Message Passing Neural Networks on Large Random Graphs","created":"2022-02-01","cited_by_count":59},{"id":"2110.15174","title":"On Provable Benefits of Depth in Training Graph Convolutional Networks","created":"2021-10-28","cited_by_count":58},{"id":"2306.13596","title":"Max-Margin Token Selection in Attention Mechanism","created":"2023-06-23","cited_by_count":58},{"id":"2112.03968","title":"Learning Theory Can (Sometimes) Explain Generalisation in Graph Neural Networks","created":"2021-12-07","cited_by_count":51},{"id":"2306.03435","title":"On the Role of Attention in Prompt-tuning","created":"2023-06-06","cited_by_count":50},{"id":"2206.01717","title":"A Theoretical Analysis on Feature Learning in Neural Networks: Emergence from Inputs and Advantage over Fixed Features","created":"2022-06-03","cited_by_count":49},{"id":"2305.08048","title":"Towards Understanding the Generalization of Graph Neural Networks","created":"2023-05-14","cited_by_count":41},{"id":"2205.06226","title":"The Mechanism of Prediction Head in Non-contrastive Self-supervised Learning","created":"2022-05-12","cited_by_count":38},{"id":"2306.04073","title":"Patch-level Routing in Mixture-of-Experts is Provably Sample-efficient for Convolutional Neural Networks","created":"2023-06-07","cited_by_count":35},{"id":"2402.15607","title":"How Do Nonlinear Transformers Learn and Generalize in In-Context Learning?","created":"2024-02-23","cited_by_count":35},{"id":"2006.08550","title":"Optimization and Generalization Analysis of Transduction through Gradient Boosting and Application to Multi-scale Graph Neural Networks","created":"2020-06-15","cited_by_count":31},{"id":"2006.14117","title":"Fast Learning of Graph Neural Networks with Guaranteed Generalizability: One-hidden-layer Case","created":"2020-06-25","cited_by_count":24},{"id":"2207.03584","title":"Generalization Guarantee of Training Graph Convolutional Networks with Graph Topology Sampling","created":"2022-07-07","cited_by_count":23},{"id":"1802.06463","title":"Guaranteed Recovery of One-Hidden-Layer Neural Networks via Cross Entropy","created":"2018-02-18","cited_by_count":22},{"id":"2310.16173","title":"On the Convergence and Sample Complexity Analysis of Deep Q-Networks with $\\epsilon$-Greedy Exploration","created":"2023-10-24","cited_by_count":17},{"id":"2302.02922","title":"Joint Edge-Model Sparse Learning is Provably Efficient for Graph Neural Networks","created":"2023-02-06","cited_by_count":16},{"id":"2308.11129","title":"Enhancing Graph Transformers with Hierarchical Distance Structural Encoding","created":"2023-08-22","cited_by_count":16},{"id":"2309.12971","title":"Higher-order Graph Convolutional Network with Flower-Petals Laplacians on Simplicial Complexes","created":"2023-09-22","cited_by_count":15},{"id":"2207.03615","title":"Learning and generalization of one-hidden-layer neural networks, going beyond standard Gaussian data","created":"2022-07-07","cited_by_count":8},{"id":"1411.7200","title":"Localized Complexities for Transductive Learning","created":"2014-11-26","cited_by_count":6},{"id":"2403.07310","title":"How does promoting the minority fraction affect generalization? A theoretical study of the one-hidden-layer neural network on group imbalance","created":"2024-03-12","cited_by_count":6}],"next_cursor":null}