{"list":"other","total":57,"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":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1810.00826","title":"How Powerful are Graph Neural Networks?","created":"2018-10-01","cited_by_count":4393},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"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":"2005.00687","title":"Open Graph Benchmark: Datasets for Machine Learning on Graphs","created":"2020-05-02","cited_by_count":2163},{"id":"2106.10199","title":"BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models","created":"2021-06-18","cited_by_count":1245},{"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":"2110.04366","title":"Towards a Unified View of Parameter-Efficient Transfer Learning","created":"2021-10-08","cited_by_count":872},{"id":"2005.00247","title":"AdapterFusion: Non-Destructive Task Composition for Transfer Learning","created":"2020-05-01","cited_by_count":788},{"id":"2012.13255","title":"Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning","created":"2020-12-22","cited_by_count":671},{"id":"2106.03893","title":"Rethinking Graph Transformers with Spectral Attention","created":"2021-06-07","cited_by_count":473},{"id":"2106.04647","title":"Compacter: Efficient Low-Rank Hypercomplex Adapter Layers","created":"2021-06-08","cited_by_count":460},{"id":"2007.07779","title":"AdapterHub: A Framework for Adapting Transformers","created":"2020-07-15","cited_by_count":444},{"id":"2103.09430","title":"OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs","created":"2021-03-17","cited_by_count":329},{"id":"2002.01808","title":"K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters","created":"2020-02-05","cited_by_count":319},{"id":"2006.15437","title":"GPT-GNN: Generative Pre-Training of Graph Neural Networks","created":"2020-06-27","cited_by_count":303},{"id":"2210.08823","title":"Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuning","created":"2022-10-17","cited_by_count":294},{"id":"2106.04489","title":"Parameter-efficient Multi-task Fine-tuning for Transformers via Shared Hypernetworks","created":"2021-06-08","cited_by_count":284},{"id":"2104.00272","title":"Mesh Graphormer","created":"2021-04-01","cited_by_count":265},{"id":"1911.03437","title":"SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization","created":"2019-11-08","cited_by_count":254},{"id":"2110.07904","title":"SPoT: Better Frozen Model Adaptation through Soft Prompt Transfer","created":"2021-10-15","cited_by_count":235},{"id":"2010.11918","title":"AdapterDrop: On the Efficiency of Adapters in Transformers","created":"2020-10-22","cited_by_count":224},{"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":"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":"2001.05140","title":"Graph-Bert: Only Attention is Needed for Learning Graph Representations","created":"2020-01-15","cited_by_count":177},{"id":"2110.07577","title":"UniPELT: A Unified Framework for Parameter-Efficient Language Model Tuning","created":"2021-10-14","cited_by_count":162},{"id":"2110.00987","title":"Motif-based Graph Self-Supervised Learning for Molecular Property Prediction","created":"2021-10-03","cited_by_count":159},{"id":"2106.05667","title":"GraphiT: Encoding Graph Structure in Transformers","created":"2021-06-10","cited_by_count":147},{"id":"2206.04910","title":"NAGphormer: A Tokenized Graph Transformer for Node Classification in Large Graphs","created":"2022-06-10","cited_by_count":137},{"id":"2212.03145","title":"FacT: Factor-Tuning for Lightweight Adaptation on Vision Transformer","created":"2022-12-06","cited_by_count":133},{"id":"2303.02861","title":"Multitask Prompt Tuning Enables Parameter-Efficient Transfer Learning","created":"2023-03-06","cited_by_count":115},{"id":"2202.08455","title":"Transformer for Graphs: An Overview from Architecture Perspective","created":"2022-02-17","cited_by_count":107},{"id":"2303.01028","title":"Specformer: Spectral Graph Neural Networks Meet Transformers","created":"2023-03-02","cited_by_count":102},{"id":"2002.08264","title":"Molecule Attention Transformer","created":"2020-02-19","cited_by_count":92},{"id":"2301.01821","title":"Parameter-Efficient Fine-Tuning Design Spaces","created":"2023-01-04","cited_by_count":67},{"id":"2110.13094","title":"Gophormer: Ego-Graph Transformer for Node Classification","created":"2021-10-25","cited_by_count":63},{"id":"2301.12132","title":"AutoPEFT: Automatic Configuration Search for Parameter-Efficient Fine-Tuning","created":"2023-01-28","cited_by_count":49},{"id":"2001.10667","title":"Interpretable Rumor Detection in Microblogs by Attending to User Interactions","created":"2020-01-29","cited_by_count":44},{"id":"2210.05062","title":"Relational Attention: Generalizing Transformers for Graph-Structured Tasks","created":"2022-10-11","cited_by_count":41},{"id":"2205.00305","title":"AdapterBias: Parameter-efficient Token-dependent Representation Shift for Adapters in NLP Tasks","created":"2022-04-30","cited_by_count":29},{"id":"2210.00788","title":"Towards a Unified View on Visual Parameter-Efficient Transfer Learning","created":"2022-10-03","cited_by_count":25},{"id":"2302.11050","title":"Edgeformers: Graph-Empowered Transformers for Representation Learning on Textual-Edge Networks","created":"2023-02-21","cited_by_count":23},{"id":"2301.13510","title":"3D Former: Monocular Scene Reconstruction with 3D SDF Transformers","created":"2023-01-31","cited_by_count":8},{"id":"2303.00690","title":"Rethinking Efficient Tuning Methods from a Unified Perspective","created":"2023-03-01","cited_by_count":6}],"next_cursor":null}