{"list":"other","total":83,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"id":"1901.00596","title":"A Comprehensive Survey on Graph Neural Networks","created":"2019-01-03","cited_by_count":2919},{"id":"2004.11362","title":"Supervised Contrastive Learning","created":"2020-04-23","cited_by_count":2829},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"2005.00687","title":"Open Graph Benchmark: Datasets for Machine Learning on Graphs","created":"2020-05-02","cited_by_count":2163},{"id":"1805.01978","title":"Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination","created":"2018-05-05","cited_by_count":1845},{"id":"1703.04730","title":"Understanding Black-box Predictions via Influence Functions","created":"2017-03-14","cited_by_count":1741},{"id":"2009.14794","title":"Rethinking Attention with Performers","created":"2020-09-30","cited_by_count":1601},{"id":"1812.08434","title":"Graph Neural Networks: A Review of Methods and Applications","created":"2018-12-20","cited_by_count":1576},{"id":"2005.10242","title":"Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere","created":"2020-05-20","cited_by_count":1405},{"id":"2303.17760","title":"CAMEL: Communicative Agents for \"Mind\" Exploration of Large Language Model Society","created":"2023-03-31","cited_by_count":1395},{"id":"1901.05555","title":"Class-Balanced Loss Based on Effective Number of Samples","created":"2019-01-16","cited_by_count":1245},{"id":"2010.13902","title":"Graph Contrastive Learning with Augmentations","created":"2020-10-22","cited_by_count":1208},{"id":"2301.00774","title":"SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot","created":"2023-01-02","cited_by_count":1121},{"id":"1711.03213","title":"CyCADA: Cycle-Consistent Adversarial Domain Adaptation","created":"2017-11-08","cited_by_count":1082},{"id":"1703.00564","title":"MoleculeNet: A Benchmark for Molecular Machine Learning","created":"2017-03-02","cited_by_count":1051},{"id":"1807.05520","title":"Deep Clustering for Unsupervised Learning of Visual Features","created":"2018-07-15","cited_by_count":1028},{"id":"1905.12265","title":"Strategies for Pre-training Graph Neural Networks","created":"2019-05-29","cited_by_count":971},{"id":"2007.02133","title":"Simple and Deep Graph Convolutional Networks","created":"2020-07-04","cited_by_count":860},{"id":"1802.09691","title":"Link Prediction Based on Graph Neural Networks","created":"2018-02-27","cited_by_count":832},{"id":"1910.09217","title":"Decoupling Representation and Classifier for Long-Tailed Recognition","created":"2019-10-21","cited_by_count":809},{"id":"2306.11695","title":"A Simple and Effective Pruning Approach for Large Language Models","created":"2023-06-20","cited_by_count":800},{"id":"2205.12454","title":"Recipe for a General, Powerful, Scalable Graph Transformer","created":"2022-05-25","cited_by_count":713},{"id":"1812.05159","title":"An Empirical Study of Example Forgetting during Deep Neural Network Learning","created":"2018-12-12","cited_by_count":678},{"id":"2005.04966","title":"Prototypical Contrastive Learning of Unsupervised Representations","created":"2020-05-11","cited_by_count":640},{"id":"2010.04592","title":"Contrastive Learning with Hard Negative Samples","created":"2020-10-09","cited_by_count":628},{"id":"2310.09478","title":"MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning","created":"2023-10-14","cited_by_count":625},{"id":"1907.04931","title":"GraphSAINT: Graph Sampling Based Inductive Learning Method","created":"2019-07-10","cited_by_count":618},{"id":"2007.07314","title":"Long-tail learning via logit adjustment","created":"2020-07-14","cited_by_count":618},{"id":"1710.01878","title":"To prune, or not to prune: exploring the efficacy of pruning for model compression","created":"2017-10-05","cited_by_count":603},{"id":"1802.10349","title":"Learning to Adapt Structured Output Space for Semantic Segmentation","created":"2018-02-28","cited_by_count":584},{"id":"2107.07075","title":"Deep Learning on a Data Diet: Finding Important Examples Early in Training","created":"2021-07-15","cited_by_count":533},{"id":"2006.05929","title":"Dataset Condensation with Gradient Matching","created":"2020-06-10","cited_by_count":516},{"id":"2004.05718","title":"Principal Neighbourhood Aggregation for Graph Nets","created":"2020-04-12","cited_by_count":478},{"id":"2205.10803","title":"GraphMAE: Self-Supervised Masked Graph Autoencoders","created":"2022-05-22","cited_by_count":448},{"id":"2203.11932","title":"Dataset Distillation by Matching Training Trajectories","created":"2022-03-22","cited_by_count":442},{"id":"2110.04596","title":"Deep Long-Tailed Learning: A Survey","created":"2021-10-09","cited_by_count":417},{"id":"2005.07683","title":"Movement Pruning: Adaptive Sparsity by Fine-Tuning","created":"2020-05-15","cited_by_count":403},{"id":"2012.09740","title":"Understanding the Behaviour of Contrastive Loss","created":"2020-12-15","cited_by_count":398},{"id":"2401.15024","title":"SliceGPT: Compress Large Language Models by Deleting Rows and Columns","created":"2024-01-26","cited_by_count":385},{"id":"2110.04181","title":"Dataset Condensation with Distribution Matching","created":"2021-10-08","cited_by_count":365},{"id":"1906.11829","title":"Selection via Proxy: Efficient Data Selection for Deep Learning","created":"2019-06-26","cited_by_count":339},{"id":"2106.07594","title":"Graph Contrastive Learning Automated","created":"2021-06-10","cited_by_count":287},{"id":"2003.05176","title":"Equalization Loss for Long-Tailed Object Recognition","created":"2020-03-11","cited_by_count":285},{"id":"2103.12051","title":"SSD: A Unified Framework for Self-Supervised Outlier Detection","created":"2021-03-22","cited_by_count":264},{"id":"2012.10630","title":"GLISTER: Generalization based Data Subset Selection for Efficient and Robust Learning","created":"2020-12-19","cited_by_count":226},{"id":"2107.13034","title":"Dataset Distillation with Infinitely Wide Convolutional Networks","created":"2021-07-27","cited_by_count":218},{"id":"2303.10158","title":"Data-centric Artificial Intelligence: A Survey","created":"2023-03-17","cited_by_count":203},{"id":"1802.09841","title":"Adversarial Active Learning for Deep Networks: a Margin Based Approach","created":"2018-02-27","cited_by_count":158},{"id":"2103.08826","title":"GraphSMOTE: Imbalanced Node Classification on Graphs with Graph Neural Networks","created":"2021-03-16","cited_by_count":147},{"id":"2008.05723","title":"Contextual Diversity for Active Learning","created":"2020-08-13","cited_by_count":139},{"id":"2205.09329","title":"Dataset Pruning: Reducing Training Data by Examining Generalization Influence","created":"2022-05-19","cited_by_count":133},{"id":"2006.11165","title":"Backdoor Attacks to Graph Neural Networks","created":"2020-06-19","cited_by_count":128},{"id":"2104.13963","title":"Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments with Support Samples","created":"2021-04-28","cited_by_count":114},{"id":"2303.04947","title":"InfoBatch: Lossless Training Speed Up by Unbiased Dynamic Data Pruning","created":"2023-03-08","cited_by_count":90},{"id":"2006.05057","title":"Towards More Practical Adversarial Attacks on Graph Neural Networks","created":"2020-06-09","cited_by_count":76},{"id":"2304.14407","title":"ChatVideo: A Tracklet-centric Multimodal and Versatile Video Understanding System","created":"2023-04-27","cited_by_count":65},{"id":"2204.07321","title":"Graph Pooling for Graph Neural Networks: Progress, Challenges, and Opportunities","created":"2022-04-15","cited_by_count":52},{"id":"2106.02817","title":"ImGAGN:Imbalanced Network Embedding via Generative Adversarial Graph Networks","created":"2021-06-05","cited_by_count":51},{"id":"2310.05174","title":"GSLB: The Graph Structure Learning Benchmark","created":"2023-10-08","cited_by_count":50},{"id":"2111.12621","title":"Accelerating Deep Learning with Dynamic Data Pruning","created":"2021-11-24","cited_by_count":43},{"id":"2402.02653","title":"Learning with Mixture of Prototypes for Out-of-Distribution Detection","created":"2024-02-05","cited_by_count":43},{"id":"2006.05482","title":"Coresets for Near-Convex Functions","created":"2020-06-09","cited_by_count":38},{"id":"2401.04578","title":"Effective pruning of web-scale datasets based on complexity of concept clusters","created":"2024-01-09","cited_by_count":34},{"id":"2406.18937","title":"Federated Graph Semantic and Structural Learning","created":"2024-06-27","cited_by_count":30},{"id":"2110.03613","title":"A Data-Centric Approach for Training Deep Neural Networks with Less Data","created":"2021-10-07","cited_by_count":28},{"id":"2402.05011","title":"Navigating Complexity: Toward Lossless Graph Condensation via Expanding Window Matching","created":"2024-02-07","cited_by_count":28},{"id":"2112.00238","title":"Imbalanced Graph Classification via Graph-of-Graph Neural Networks","created":"2021-12-01","cited_by_count":27},{"id":"2107.06869","title":"Core-set Sampling for Efficient Neural Architecture Search","created":"2021-07-08","cited_by_count":23},{"id":"2309.15123","title":"Uncovering Neural Scaling Laws in Molecular Representation Learning","created":"2023-09-15","cited_by_count":23},{"id":"2311.01002","title":"Robust Data Pruning under Label Noise via Maximizing Re-labeling Accuracy","created":"2023-11-02","cited_by_count":20},{"id":"2310.03295","title":"Can pre-trained models assist in dataset distillation?","created":"2023-10-05","cited_by_count":12},{"id":"2303.06199","title":"Turning Strengths into Weaknesses: A Certified Robustness Inspired Attack Framework against Graph Neural Networks","created":"2023-03-10","cited_by_count":11},{"id":"2407.11624","title":"Rethinking Fair Graph Neural Networks from Re-balancing","created":"2024-07-16","cited_by_count":11},{"id":"1708.09056","title":"Practical Attacks Against Graph-based Clustering","created":"2017-08-29","cited_by_count":9},{"id":"2311.15772","title":"Attend Who is Weak: Enhancing Graph Condensation via Cross-Free Adversarial Training","created":"2023-11-27","cited_by_count":9},{"id":"2409.01081","title":"Beyond Efficiency: Molecular Data Pruning for Enhanced Generalization","created":"2024-09-02","cited_by_count":9},{"id":"2402.04924","title":"Two Trades is not Baffled: Condensing Graph via Crafting Rational Gradient Matching","created":"2024-02-07","cited_by_count":8}],"next_cursor":null}