{"list":"other","total":116,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"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":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"2004.11362","title":"Supervised Contrastive Learning","created":"2020-04-23","cited_by_count":2829},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576},{"id":"1903.02428","title":"Fast Graph Representation Learning with PyTorch Geometric","created":"2019-03-06","cited_by_count":2434},{"id":"2212.13138","title":"Large Language Models Encode Clinical Knowledge","created":"2022-12-26","cited_by_count":1830},{"id":"2203.05557","title":"Conditional Prompt Learning for Vision-Language Models","created":"2022-03-10","cited_by_count":1433},{"id":"2010.13902","title":"Graph Contrastive Learning with Augmentations","created":"2020-10-22","cited_by_count":1208},{"id":"1703.00564","title":"MoleculeNet: A Benchmark for Molecular Machine Learning","created":"2017-03-02","cited_by_count":1051},{"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":"2211.09085","title":"Galactica: A Large Language Model for Science","created":"2022-11-16","cited_by_count":744},{"id":"2007.08663","title":"TUDataset: A collection of benchmark datasets for learning with graphs","created":"2020-07-16","cited_by_count":728},{"id":"2210.03117","title":"MaPLe: Multi-modal Prompt Learning","created":"2022-10-06","cited_by_count":687},{"id":"2003.00982","title":"Benchmarking Graph Neural Networks","created":"2020-03-02","cited_by_count":680},{"id":"2006.05582","title":"Contrastive Multi-View Representation Learning on Graphs","created":"2020-06-10","cited_by_count":652},{"id":"2109.14084","title":"VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding","created":"2021-09-28","cited_by_count":602},{"id":"1911.06455","title":"Graph Transformer Networks","created":"2019-11-06","cited_by_count":523},{"id":"2209.14734","title":"DiGress: Discrete Denoising diffusion for graph generation","created":"2022-09-29","cited_by_count":520},{"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":"2112.02413","title":"PointCLIP: Point Cloud Understanding by CLIP","created":"2021-12-04","cited_by_count":463},{"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":"2106.13043","title":"AudioCLIP: Extending CLIP to Image, Text and Audio","created":"2021-06-24","cited_by_count":339},{"id":"2006.09252","title":"Improving Graph Neural Network Expressivity via Subgraph Isomorphism Counting","created":"2020-06-16","cited_by_count":313},{"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":"2110.11499","title":"Wav2CLIP: Learning Robust Audio Representations From CLIP","created":"2021-10-21","cited_by_count":213},{"id":"2306.15794","title":"HyenaDNA: Long-Range Genomic Sequence Modeling at Single Nucleotide Resolution","created":"2023-06-27","cited_by_count":194},{"id":"2312.02783","title":"Large Language Models on Graphs: A Comprehensive Survey","created":"2023-12-05","cited_by_count":192},{"id":"2201.08860","title":"GreaseLM: Graph REASoning Enhanced Language Models for Question Answering","created":"2022-01-21","cited_by_count":171},{"id":"2202.03104","title":"SimGRACE: A Simple Framework for Graph Contrastive Learning without Data Augmentation","created":"2022-02-07","cited_by_count":171},{"id":"2302.08043","title":"GraphPrompt: Unifying Pre-Training and Downstream Tasks for Graph Neural Networks","created":"2023-02-16","cited_by_count":167},{"id":"2210.14709","title":"Learning on Large-scale Text-attributed Graphs via Variational Inference","created":"2022-10-26","cited_by_count":155},{"id":"2307.01504","title":"All in One: Multi-task Prompting for Graph Neural Networks","created":"2023-07-04","cited_by_count":148},{"id":"2105.02605","title":"GraphFormers: GNN-nested Transformers for Representation Learning on Textual Graph","created":"2021-05-06","cited_by_count":143},{"id":"2111.00064","title":"Node Feature Extraction by Self-Supervised Multi-scale Neighborhood Prediction","created":"2021-10-29","cited_by_count":138},{"id":"2209.05481","title":"A Molecular Multimodal Foundation Model Associating Molecule Graphs with Natural Language","created":"2022-09-12","cited_by_count":131},{"id":"2004.03497","title":"ProGen: Language Modeling for Protein Generation","created":"2020-03-08","cited_by_count":128},{"id":"2310.12798","title":"MolCA: Molecular Graph-Language Modeling with Cross-Modal Projector and Uni-Modal Adapter","created":"2023-10-19","cited_by_count":128},{"id":"2108.13161","title":"Differentiable Prompt Makes Pre-trained Language Models Better Few-shot Learners","created":"2021-08-30","cited_by_count":115},{"id":"2206.11140","title":"Understanding and Extending Subgraph GNNs by Rethinking Their Symmetries","created":"2022-06-22","cited_by_count":112},{"id":"2209.15240","title":"Universal Prompt Tuning for Graph Neural Networks","created":"2022-09-30","cited_by_count":100},{"id":"2305.12600","title":"PRODIGY: Enabling In-context Learning Over Graphs","created":"2023-05-21","cited_by_count":98},{"id":"2010.15363","title":"Model-Agnostic Counterfactual Reasoning for Eliminating Popularity Bias in Recommender System","created":"2020-10-29","cited_by_count":94},{"id":"1410.3314","title":"Propagation Kernels","created":"2014-10-13","cited_by_count":88},{"id":"2307.08849","title":"Autoregressive Diffusion Model for Graph Generation","created":"2023-07-17","cited_by_count":83},{"id":"2102.07810","title":"HDMI: High-order Deep Multiplex Infomax","created":"2021-02-15","cited_by_count":82},{"id":"2308.06911","title":"GIT-Mol: A Multi-modal Large Language Model for Molecular Science with Graph, Image, and Text","created":"2023-08-14","cited_by_count":82},{"id":"2405.11416","title":"Discrete-state Continuous-time Diffusion for Graph Generation","created":"2024-05-19","cited_by_count":76},{"id":"2308.02565","title":"SimTeG: A Frustratingly Simple Approach Improves Textual Graph Learning","created":"2023-08-03","cited_by_count":73},{"id":"2306.13089","title":"GIMLET: A Unified Graph-Text Model for Instruction-Based Molecule Zero-Shot Learning","created":"2023-05-28","cited_by_count":70},{"id":"2305.03324","title":"Augmenting Low-Resource Text Classification with Graph-Grounded Pre-training and Prompting","created":"2023-05-05","cited_by_count":62},{"id":"2311.16534","title":"Graph Prompt Learning: A Comprehensive Survey and Beyond","created":"2023-11-28","cited_by_count":61},{"id":"2101.06323","title":"TextGNN: Improving Text Encoder via Graph Neural Network in Sponsored Search","created":"2021-01-15","cited_by_count":54},{"id":"2307.09484","title":"MolFM: A Multimodal Molecular Foundation Model","created":"2023-06-06","cited_by_count":50},{"id":"2305.12268","title":"Patton: Language Model Pretraining on Text-Rich Networks","created":"2023-05-20","cited_by_count":49},{"id":"2306.06063","title":"Virtual Node Tuning for Few-shot Node Classification","created":"2023-06-09","cited_by_count":46},{"id":"2306.03221","title":"Structural Re-weighting Improves Graph Domain Adaptation","created":"2023-06-05","cited_by_count":45},{"id":"2110.03177","title":"EE-Net: Exploitation-Exploration Neural Networks in Contextual Bandits","created":"2021-10-07","cited_by_count":44},{"id":"2212.08174","title":"Non-IID Transfer Learning on Graphs","created":"2022-12-15","cited_by_count":43},{"id":"2202.06491","title":"Adversarial Graph Contrastive Learning with Information Regularization","created":"2022-02-14","cited_by_count":38},{"id":"2302.12449","title":"SGL-PT: A Strong Graph Learner with Graph Prompt Tuning","created":"2023-02-24","cited_by_count":35},{"id":"2110.14863","title":"Graph Communal Contrastive Learning","created":"2021-10-28","cited_by_count":34},{"id":"2403.16030","title":"VCR-Graphormer: A Mini-batch Graph Transformer via Virtual Connections","created":"2024-03-24","cited_by_count":34},{"id":"2212.06858","title":"LidarCLIP or: How I Learned to Talk to Point Clouds","created":"2022-12-13","cited_by_count":33},{"id":"2305.18612","title":"Networked Time Series Imputation via Position-aware Graph Enhanced Variational Autoencoders","created":"2023-05-29","cited_by_count":32},{"id":"2210.00705","title":"SpeechCLIP: Integrating Speech with Pre-Trained Vision and Language Model","created":"2022-10-03","cited_by_count":29},{"id":"2210.03801","title":"Augmentations in Hypergraph Contrastive Learning: Fabricated and Generative","created":"2022-10-07","cited_by_count":29},{"id":"2308.14181","title":"Class-Imbalanced Graph Learning without Class Rebalancing","created":"2023-08-27","cited_by_count":29},{"id":"1909.03500","title":"Self-paced Ensemble for Highly Imbalanced Massive Data Classification","created":"2019-09-08","cited_by_count":28},{"id":"2310.15109","title":"GRENADE: Graph-Centric Language Model for Self-Supervised Representation Learning on Text-Attributed Graphs","created":"2023-10-23","cited_by_count":28},{"id":"2308.15651","title":"Ensuring User-side Fairness in Dynamic Recommender Systems","created":"2023-08-29","cited_by_count":27},{"id":"2404.00225","title":"Heterogeneous Contrastive Learning for Foundation Models and Beyond","created":"2024-03-30","cited_by_count":27},{"id":"2403.10667","title":"Towards Unified Multi-Modal Personalization: Large Vision-Language Models for Generative Recommendation and Beyond","created":"2024-03-15","cited_by_count":25},{"id":"2410.21520","title":"LLM-Forest: Ensemble Learning of LLMs with Graph-Augmented Prompts for Data Imputation","created":"2024-10-28","cited_by_count":25},{"id":"2205.10282","title":"Heterformer: Transformer-based Deep Node Representation Learning on Heterogeneous Text-Rich Networks","created":"2022-05-20","cited_by_count":24},{"id":"2310.04470","title":"Hierarchical Multi-Marginal Optimal Transport for Network Alignment","created":"2023-10-06","cited_by_count":24},{"id":"2202.07893","title":"A Survey of Pretraining on Graphs: Taxonomy, Methods, and Applications","created":"2022-02-16","cited_by_count":23},{"id":"2309.16014","title":"Graph-level Representation Learning with Joint-Embedding Predictive Architectures","created":"2023-09-27","cited_by_count":22},{"id":"2308.10808","title":"Graph Neural Bandits","created":"2023-08-21","cited_by_count":20},{"id":"2109.03560","title":"X-GOAL: Multiplex Heterogeneous Graph Prototypical Contrastive Learning","created":"2021-09-08","cited_by_count":19},{"id":"2208.09905","title":"MentorGNN: Deriving Curriculum for Pre-Training GNNs","created":"2022-08-21","cited_by_count":18},{"id":"2102.07751","title":"Deep Co-Attention Network for Multi-View Subspace Learning","created":"2021-02-15","cited_by_count":17},{"id":"2107.02168","title":"DPPIN: A Biological Repository of Dynamic Protein-Protein Interaction Network Data","created":"2021-07-05","cited_by_count":17},{"id":"2312.10073","title":"Data Scarcity in Recommendation Systems: A Survey","created":"2023-12-08","cited_by_count":17},{"id":"2210.11065","title":"MovieCLIP: Visual Scene Recognition in Movies","created":"2022-10-20","cited_by_count":16},{"id":"2105.09401","title":"Heterogeneous Contrastive Learning","created":"2021-05-19","cited_by_count":15},{"id":"2206.00006","title":"COIN: Co-Cluster Infomax for Bipartite Graphs","created":"2022-05-31","cited_by_count":14},{"id":"2306.03561","title":"CIN++: Enhancing Topological Message Passing","created":"2023-06-06","cited_by_count":14}],"next_cursor":"100"}