{"list":"other","total":54,"rows":[{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"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":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"1903.02428","title":"Fast Graph Representation Learning with PyTorch Geometric","created":"2019-03-06","cited_by_count":2434},{"id":"2005.00687","title":"Open Graph Benchmark: Datasets for Machine Learning on Graphs","created":"2020-05-02","cited_by_count":2163},{"id":"1703.04730","title":"Understanding Black-box Predictions via Influence Functions","created":"2017-03-14","cited_by_count":1741},{"id":"2010.13902","title":"Graph Contrastive Learning with Augmentations","created":"2020-10-22","cited_by_count":1208},{"id":"1905.12265","title":"Strategies for Pre-training Graph Neural Networks","created":"2019-05-29","cited_by_count":971},{"id":"1812.05159","title":"An Empirical Study of Example Forgetting during Deep Neural Network Learning","created":"2018-12-12","cited_by_count":678},{"id":"1706.08566","title":"SchNet: A continuous-filter convolutional neural network for modeling quantum interactions","created":"2017-06-26","cited_by_count":571},{"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":"2206.14486","title":"Beyond neural scaling laws: beating power law scaling via data pruning","created":"2022-06-29","cited_by_count":528},{"id":"2205.10803","title":"GraphMAE: Self-Supervised Masked Graph Autoencoders","created":"2022-05-22","cited_by_count":448},{"id":"2102.03150","title":"Equivariant message passing for the prediction of tensorial properties and molecular spectra","created":"2021-02-05","cited_by_count":441},{"id":"1906.11829","title":"Selection via Proxy: Efficient Data Selection for Deep Learning","created":"2019-06-26","cited_by_count":339},{"id":"2302.03169","title":"Data Selection for Language Models via Importance Resampling","created":"2023-02-06","cited_by_count":329},{"id":"2103.00123","title":"GRAD-MATCH: Gradient Matching based Data Subset Selection for Efficient Deep Model Training","created":"2021-02-27","cited_by_count":274},{"id":"2012.10630","title":"GLISTER: Generalization based Data Subset Selection for Efficient and Robust Learning","created":"2020-12-19","cited_by_count":226},{"id":"2106.06130","title":"ChemRL-GEM: Geometry Enhanced Molecular Representation Learning for Property Prediction","created":"2021-06-11","cited_by_count":204},{"id":"2006.03875","title":"Coresets via Bilevel Optimization for Continual Learning and Streaming","created":"2020-06-06","cited_by_count":192},{"id":"1802.09841","title":"Adversarial Active Learning for Deep Networks: a Margin Based Approach","created":"2018-02-27","cited_by_count":158},{"id":"2109.03764","title":"Active Learning by Acquiring Contrastive Examples","created":"2021-09-08","cited_by_count":156},{"id":"2204.08499","title":"DeepCore: A Comprehensive Library for Coreset Selection in Deep Learning","created":"2022-04-18","cited_by_count":147},{"id":"2206.08452","title":"GOOD: A Graph Out-of-Distribution Benchmark","created":"2022-06-16","cited_by_count":141},{"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":"2303.04947","title":"InfoBatch: Lossless Training Speed Up by Unbiased Dynamic Data Pruning","created":"2023-03-08","cited_by_count":90},{"id":"2311.12399","title":"A Survey of Graph Meets Large Language Model: Progress and Future Directions","created":"2023-11-21","cited_by_count":85},{"id":"2402.11235","title":"ZeroG: Investigating Cross-dataset Zero-shot Transferability in Graphs","created":"2024-02-17","cited_by_count":85},{"id":"2107.00717","title":"SIMILAR: Submodular Information Measures Based Active Learning In Realistic Scenarios","created":"2021-07-01","cited_by_count":84},{"id":"1605.06423","title":"Coresets for Scalable Bayesian Logistic Regression","created":"2016-05-20","cited_by_count":79},{"id":"2106.07760","title":"RETRIEVE: Coreset Selection for Efficient and Robust Semi-Supervised Learning","created":"2021-06-14","cited_by_count":74},{"id":"2206.13602","title":"Molecular Geometry Pretraining with SE(3)-Invariant Denoising Distance Matching","created":"2022-06-27","cited_by_count":68},{"id":"1710.05053","title":"Automated Scalable Bayesian Inference via Hilbert Coresets","created":"2017-10-13","cited_by_count":55},{"id":"2307.09484","title":"MolFM: A Multimodal Molecular Foundation Model","created":"2023-06-06","cited_by_count":50},{"id":"2207.08806","title":"Unified 2D and 3D Pre-Training of Molecular Representations","created":"2022-07-14","cited_by_count":45},{"id":"2111.12621","title":"Accelerating Deep Learning with Dynamic Data Pruning","created":"2021-11-24","cited_by_count":43},{"id":"1910.13540","title":"Small-GAN: Speeding Up GAN Training Using Core-sets","created":"2019-10-29","cited_by_count":41},{"id":"2310.04292","title":"Towards Foundational Models for Molecular Learning on Large-Scale Multi-Task Datasets","created":"2023-10-06","cited_by_count":39},{"id":"2402.13040","title":"Text-Guided Molecule Generation with Diffusion Language Model","created":"2024-02-20","cited_by_count":31},{"id":"2211.10590","title":"Bidirectional Generation of Structure and Properties Through a Single Molecular Foundation Model","created":"2022-11-19","cited_by_count":25},{"id":"2309.15123","title":"Uncovering Neural Scaling Laws in Molecular Representation Learning","created":"2023-09-15","cited_by_count":23},{"id":"2402.07225","title":"Rethinking Graph Masked Autoencoders through Alignment and Uniformity","created":"2024-02-11","cited_by_count":22},{"id":"2404.14986","title":"$\\texttt{MiniMol}$: A Parameter-Efficient Foundation Model for Molecular Learning","created":"2024-04-23","cited_by_count":20},{"id":"2107.04984","title":"SVP-CF: Selection via Proxy for Collaborative Filtering Data","created":"2021-07-11","cited_by_count":14},{"id":"2311.01038","title":"Better with Less: A Data-Active Perspective on Pre-Training Graph Neural Networks","created":"2023-11-02","cited_by_count":14},{"id":"2211.02657","title":"MolE: a molecular foundation model for drug discovery","created":"2022-11-03","cited_by_count":12},{"id":"2303.11101","title":"Coreset Sampling from Open-Set for Fine-Grained Self-Supervised Learning","created":"2023-03-20","cited_by_count":12},{"id":"2310.08782","title":"Selectivity Drives Productivity: Efficient Dataset Pruning for Enhanced Transfer Learning","created":"2023-10-13","cited_by_count":11},{"id":"2307.10438","title":"Uncertainty Quantification for Molecular Property Predictions with Graph Neural Architecture Search","created":"2023-07-19","cited_by_count":8},{"id":"2408.04400","title":"DIVE: Subgraph Disagreement for Graph Out-of-Distribution Generalization","created":"2024-08-08","cited_by_count":7}],"next_cursor":null}