{"list":"other","total":58,"rows":[{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1710.10903","title":"Graph Attention Networks","created":"2017-10-30","cited_by_count":8923},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"1801.07829","title":"Dynamic Graph CNN for Learning on Point Clouds","created":"2018-01-24","cited_by_count":2223},{"id":"2005.00687","title":"Open Graph Benchmark: Datasets for Machine Learning on Graphs","created":"2020-05-02","cited_by_count":2163},{"id":"1412.6550","title":"FitNets: Hints for Thin Deep Nets","created":"2014-12-19","cited_by_count":1653},{"id":"1911.11763","title":"SuperGlue: Learning Feature Matching with Graph Neural Networks","created":"2019-11-26","cited_by_count":1443},{"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":"2012.00364","title":"Pre-Trained Image Processing Transformer","created":"2020-12-01","cited_by_count":893},{"id":"2205.06175","title":"A Generalist Agent","created":"2022-05-12","cited_by_count":808},{"id":"1506.04757","title":"Image-based Recommendations on Styles and Substitutes","created":"2015-06-15","cited_by_count":706},{"id":"1801.10247","title":"FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling","created":"2018-01-30","cited_by_count":584},{"id":"2011.02260","title":"Graph Neural Networks in Recommender Systems: A Survey","created":"2020-11-04","cited_by_count":494},{"id":"2004.05718","title":"Principal Neighbourhood Aggregation for Graph Nets","created":"2020-04-12","cited_by_count":478},{"id":"2102.04906","title":"Dynamic Neural Networks: A Survey","created":"2021-02-09","cited_by_count":408},{"id":"1909.01315","title":"Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks","created":"2019-09-03","cited_by_count":242},{"id":"1806.08730","title":"The Natural Language Decathlon: Multitask Learning as Question Answering","created":"2018-06-20","cited_by_count":236},{"id":"1903.05134","title":"Universally Slimmable Networks and Improved Training Techniques","created":"2019-03-12","cited_by_count":221},{"id":"2101.00121","title":"WARP: Word-level Adversarial ReProgramming","created":"2021-01-01","cited_by_count":221},{"id":"2301.12900","title":"DepGraph: Towards Any Structural Pruning","created":"2023-01-30","cited_by_count":203},{"id":"1812.10528","title":"Adversarial Attack and Defense on Graph Data: A Survey","created":"2018-12-26","cited_by_count":167},{"id":"1411.0030","title":"A* Sampling","created":"2014-10-31","cited_by_count":151},{"id":"1711.11503","title":"Convolutional Networks with Adaptive Inference Graphs","created":"2017-11-30","cited_by_count":148},{"id":"2003.10477","title":"Distilling Knowledge from Graph Convolutional Networks","created":"2020-03-23","cited_by_count":129},{"id":"2301.07014","title":"Dataset Distillation: A Comprehensive Review","created":"2023-01-17","cited_by_count":127},{"id":"1806.11146","title":"Adversarial Reprogramming of Neural Networks","created":"2018-06-28","cited_by_count":116},{"id":"2210.16774","title":"Dataset Distillation via Factorization","created":"2022-10-30","cited_by_count":115},{"id":"2303.00980","title":"Learning to Grow Pretrained Models for Efficient Transformer Training","created":"2023-03-02","cited_by_count":83},{"id":"2010.05421","title":"Factorizable Graph Convolutional Networks","created":"2020-10-12","cited_by_count":79},{"id":"2210.17409","title":"Deep Model Reassembly","created":"2022-10-24","cited_by_count":78},{"id":"2202.10629","title":"Model Reprogramming: Resource-Efficient Cross-Domain Machine Learning","created":"2022-02-22","cited_by_count":64},{"id":"2207.03337","title":"Factorizing Knowledge in Neural Networks","created":"2022-07-04","cited_by_count":59},{"id":"2110.06923","title":"Object DGCNN: 3D Object Detection using Dynamic Graphs","created":"2021-10-13","cited_by_count":58},{"id":"2105.07519","title":"Graph-Free Knowledge Distillation for Graph Neural Networks","created":"2021-05-16","cited_by_count":46},{"id":"2108.03658","title":"One-Shot Object Affordance Detection in the Wild","created":"2021-08-08","cited_by_count":40},{"id":"2111.04964","title":"On Representation Knowledge Distillation for Graph Neural Networks","created":"2021-11-09","cited_by_count":38},{"id":"2106.03772","title":"Learning Dynamics via Graph Neural Networks for Human Pose Estimation and Tracking","created":"2021-06-07","cited_by_count":37},{"id":"2203.09507","title":"Towards Data-Efficient Detection Transformers","created":"2022-03-17","cited_by_count":34},{"id":"2003.09088","title":"Data-Free Knowledge Amalgamation via Group-Stack Dual-GAN","created":"2020-03-20","cited_by_count":32},{"id":"2009.00647","title":"Lifelong Graph Learning","created":"2020-09-01","cited_by_count":31},{"id":"2207.08224","title":"Learning with Recoverable Forgetting","created":"2022-07-17","cited_by_count":30},{"id":"2207.11681","title":"Learning Graph Neural Networks for Image Style Transfer","created":"2022-07-24","cited_by_count":29},{"id":"2101.03464","title":"SPAGAN: Shortest Path Graph Attention Network","created":"2021-01-10","cited_by_count":28},{"id":"2108.05507","title":"Distilling Holistic Knowledge with Graph Neural Networks","created":"2021-08-12","cited_by_count":26},{"id":"2109.12872","title":"Meta-Aggregator: Learning to Aggregate for 1-bit Graph Neural Networks","created":"2021-09-27","cited_by_count":25},{"id":"1801.09797","title":"Discrete Autoencoders for Sequence Models","created":"2018-01-29","cited_by_count":24},{"id":"2207.06124","title":"DynaST: Dynamic Sparse Transformer for Exemplar-Guided Image Generation","created":"2022-07-13","cited_by_count":24},{"id":"2206.06561","title":"FreeKD: Free-direction Knowledge Distillation for Graph Neural Networks","created":"2022-06-14","cited_by_count":23},{"id":"2205.02399","title":"Spot-adaptive Knowledge Distillation","created":"2022-05-05","cited_by_count":22},{"id":"2304.11595","title":"Segment Anything in Non-Euclidean Domains: Challenges and Opportunities","created":"2023-04-23","cited_by_count":16},{"id":"2108.11673","title":"Why Adversarial Reprogramming Works, When It Fails, and How to Tell the Difference","created":"2021-08-26","cited_by_count":13},{"id":"1709.05936","title":"Kernel Cross-Correlator","created":"2017-09-12","cited_by_count":12},{"id":"2206.03466","title":"Adversarial Reprogramming Revisited","created":"2022-06-07","cited_by_count":10},{"id":"2112.03695","title":"Safe Distillation Box","created":"2021-12-05","cited_by_count":9},{"id":"1910.13124","title":"Multitask Learning On Graph Neural Networks Applied To Molecular Property Predictions","created":"2019-10-29","cited_by_count":6},{"id":"2112.13966","title":"Online Adversarial Knowledge Distillation for Graph Neural Networks","created":"2021-12-28","cited_by_count":2}],"next_cursor":null}