{"list":"other","total":68,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"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":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"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":"1704.01212","title":"Neural Message Passing for Quantum Chemistry","created":"2017-04-04","cited_by_count":3487},{"id":"1508.07909","title":"Neural Machine Translation of Rare Words with Subword Units","created":"2015-08-31","cited_by_count":2918},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"1412.3555","title":"Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling","created":"2014-12-11","cited_by_count":2367},{"id":"2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","created":"2020-06-29","cited_by_count":2022},{"id":"1607.00653","title":"node2vec: Scalable Feature Learning for Networks","created":"2016-07-03","cited_by_count":1918},{"id":"1403.6652","title":"DeepWalk: Online Learning of Social Representations","created":"2014-03-26","cited_by_count":1547},{"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":"2111.09886","title":"SimMIM: A Simple Framework for Masked Image Modeling","created":"2021-11-18","cited_by_count":1153},{"id":"2404.02905","title":"Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction","created":"2024-04-03","cited_by_count":1023},{"id":"2205.12454","title":"Recipe for a General, Powerful, Scalable Graph Transformer","created":"2022-05-25","cited_by_count":713},{"id":"2012.09699","title":"A Generalization of Transformer Networks to Graphs","created":"2020-12-17","cited_by_count":661},{"id":"2006.05582","title":"Contrastive Multi-View Representation Learning on Graphs","created":"2020-06-10","cited_by_count":652},{"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":"2111.14522","title":"Understanding over-squashing and bottlenecks on graphs via curvature","created":"2021-11-29","cited_by_count":478},{"id":"2106.03893","title":"Rethinking Graph Transformers with Spectral Attention","created":"2021-06-07","cited_by_count":473},{"id":"2006.09963","title":"GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training","created":"2020-06-17","cited_by_count":463},{"id":"2106.07594","title":"Graph Contrastive Learning Automated","created":"2021-06-10","cited_by_count":287},{"id":"2303.10993","title":"A Survey on Oversmoothing in Graph Neural Networks","created":"2023-03-20","cited_by_count":247},{"id":"2310.00149","title":"One for All: Towards Training One Graph Model for All Classification Tasks","created":"2023-09-29","cited_by_count":243},{"id":"2202.03036","title":"Structure-Aware Transformer for Graph Representation Learning","created":"2022-02-07","cited_by_count":194},{"id":"2207.02505","title":"Pure Transformers are Powerful Graph Learners","created":"2022-07-06","cited_by_count":188},{"id":"2102.06514","title":"Large-Scale Representation Learning on Graphs via Bootstrapping","created":"2021-02-12","cited_by_count":186},{"id":"2110.03753","title":"From Stars to Subgraphs: Uplifting Any GNN with Local Structure Awareness","created":"2021-10-07","cited_by_count":155},{"id":"2106.12484","title":"From Canonical Correlation Analysis to Self-supervised Graph Neural Networks","created":"2021-06-23","cited_by_count":141},{"id":"2206.04910","title":"NAGphormer: A Tokenized Graph Transformer for Node Classification in Large Graphs","created":"2022-06-10","cited_by_count":137},{"id":"2306.10759","title":"SGFormer: Simplifying and Empowering Transformers for Large-Graph Representations","created":"2023-06-19","cited_by_count":133},{"id":"2304.04779","title":"GraphMAE2: A Decoding-Enhanced Masked Self-Supervised Graph Learner","created":"2023-04-10","cited_by_count":132},{"id":"2006.03548","title":"Graphon Neural Networks and the Transferability of Graph Neural Networks","created":"2020-06-05","cited_by_count":118},{"id":"2110.15438","title":"InfoGCL: Information-Aware Graph Contrastive Learning","created":"2021-10-28","cited_by_count":105},{"id":"2212.13350","title":"A Generalization of ViT/MLP-Mixer to Graphs","created":"2022-12-27","cited_by_count":93},{"id":"2411.06070","title":"GFT: Graph Foundation Model with Transferable Tree Vocabulary","created":"2024-11-09","cited_by_count":85},{"id":"2205.10053","title":"What's Behind the Mask: Understanding Masked Graph Modeling for Graph Autoencoders","created":"2022-05-20","cited_by_count":82},{"id":"2102.08786","title":"Walking Out of the Weisfeiler Leman Hierarchy: Graph Learning Beyond Message Passing","created":"2021-02-17","cited_by_count":47},{"id":"1805.11921","title":"Anonymous Walk Embeddings","created":"2018-05-30","cited_by_count":46},{"id":"2401.08514","title":"Beyond Weisfeiler-Lehman: A Quantitative Framework for GNN Expressiveness","created":"2024-01-16","cited_by_count":39},{"id":"2306.05955","title":"Path Neural Networks: Expressive and Accurate Graph Neural Networks","created":"2023-06-09","cited_by_count":32},{"id":"2412.16441","title":"Towards Graph Foundation Models: Learning Generalities Across Graphs via Task-Trees","created":"2024-12-21","cited_by_count":32},{"id":"2206.13953","title":"RAW-GNN: RAndom Walk Aggregation based Graph Neural Network","created":"2022-06-28","cited_by_count":25},{"id":"2405.21064","title":"Recurrent neural networks: vanishing and exploding gradients are not the end of the story","created":"2024-05-31","cited_by_count":25},{"id":"2412.08847","title":"MOPI-HFRS: A Multi-objective Personalized Health-aware Food Recommendation System with LLM-enhanced Interpretation","created":"2024-12-12","cited_by_count":18},{"id":"2402.08907","title":"Subgraph Pooling: Tackling Negative Transfer on Graphs","created":"2024-02-14","cited_by_count":17},{"id":"2501.01073","title":"Graph Generative Pre-trained Transformer","created":"2025-01-02","cited_by_count":17},{"id":"2312.02230","title":"A Simple and Scalable Representation for Graph Generation","created":"2023-12-04","cited_by_count":16},{"id":"1606.06235","title":"Scalable motif-aware graph clustering","created":"2016-06-20","cited_by_count":15},{"id":"2210.00248","title":"Heterogeneous Graph Contrastive Multi-view Learning","created":"2022-10-01","cited_by_count":14},{"id":"2403.08820","title":"Diet-ODIN: A Novel Framework for Opioid Misuse Detection with Interpretable Dietary Patterns","created":"2024-02-21","cited_by_count":14},{"id":"2206.11010","title":"Agent-based Graph Neural Networks","created":"2022-06-22","cited_by_count":13},{"id":"2407.01214","title":"Revisiting Random Walks for Learning on Graphs","created":"2024-07-01","cited_by_count":13},{"id":"2402.03814","title":"Masked Graph Autoencoder with Non-discrete Bandwidths","created":"2024-02-06","cited_by_count":11},{"id":"2408.00165","title":"Non-convolutional Graph Neural Networks","created":"2024-07-31","cited_by_count":11},{"id":"1809.06057","title":"Cumulative effects of triadic closure and homophily in social networks","created":"2018-09-17","cited_by_count":10},{"id":"2306.05838","title":"Expectation-Complete Graph Representations with Homomorphisms","created":"2023-06-09","cited_by_count":10},{"id":"2502.15564","title":"Adaptive Expansion for Hypergraph Learning","created":"2025-02-21","cited_by_count":7},{"id":"2007.07447","title":"Motifs for processes on networks","created":"2020-07-15","cited_by_count":6}],"next_cursor":null}