{"list":"other","total":58,"rows":[{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1706.02216","title":"Inductive Representation Learning on Large Graphs","created":"2017-06-07","cited_by_count":6320},{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"id":"1704.01212","title":"Neural Message Passing for Quantum Chemistry","created":"2017-04-04","cited_by_count":3487},{"id":"2101.03961","title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","created":"2021-01-11","cited_by_count":3073},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"1901.00596","title":"A Comprehensive Survey on Graph Neural Networks","created":"2019-01-03","cited_by_count":2919},{"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":"2006.16668","title":"GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding","created":"2020-06-30","cited_by_count":1631},{"id":"1812.08434","title":"Graph Neural Networks: A Review of Methods and Applications","created":"2018-12-20","cited_by_count":1576},{"id":"1802.09691","title":"Link Prediction Based on Graph Neural Networks","created":"2018-02-27","cited_by_count":832},{"id":"1810.02340","title":"SNIP: Single-shot Network Pruning based on Connection Sensitivity","created":"2018-10-04","cited_by_count":812},{"id":"1806.08804","title":"Hierarchical Graph Representation Learning with Differentiable Pooling","created":"2018-06-22","cited_by_count":787},{"id":"2106.05974","title":"Scaling Vision with Sparse Mixture of Experts","created":"2021-06-10","cited_by_count":747},{"id":"2003.00982","title":"Benchmarking Graph Neural Networks","created":"2020-03-02","cited_by_count":680},{"id":"2004.05718","title":"Principal Neighbourhood Aggregation for Graph Nets","created":"2020-04-12","cited_by_count":478},{"id":"2010.10783","title":"Self-supervised Graph Learning for Recommendation","created":"2020-10-21","cited_by_count":305},{"id":"2202.01169","title":"Unified Scaling Laws for Routed Language Models","created":"2022-02-02","cited_by_count":253},{"id":"2006.07739","title":"DeeperGCN: All You Need to Train Deeper GCNs","created":"2020-06-13","cited_by_count":250},{"id":"2106.04426","title":"Hash Layers For Large Sparse Models","created":"2021-06-08","cited_by_count":237},{"id":"1907.04840","title":"Sparse Networks from Scratch: Faster Training without Losing Performance","created":"2019-07-10","cited_by_count":213},{"id":"2306.08385","title":"NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classification","created":"2023-06-14","cited_by_count":210},{"id":"2206.02770","title":"Multimodal Contrastive Learning with LIMoE: the Language-Image Mixture of Experts","created":"2022-06-06","cited_by_count":203},{"id":"2112.08679","title":"Are Graph Augmentations Necessary? Simple Graph Contrastive Learning for Recommendation","created":"2021-12-16","cited_by_count":173},{"id":"1905.02850","title":"Understanding Attention and Generalization in Graph Neural Networks","created":"2019-05-08","cited_by_count":169},{"id":"2106.07476","title":"Training Graph Neural Networks with 1000 Layers","created":"2021-06-14","cited_by_count":169},{"id":"2003.01171","title":"A Semi-supervised Graph Attentive Network for Financial Fraud Detection","created":"2020-02-28","cited_by_count":151},{"id":"2110.07580","title":"Graph Condensation for Graph Neural Networks","created":"2021-10-14","cited_by_count":150},{"id":"2307.01504","title":"All in One: Multi-task Prompting for Graph Neural Networks","created":"2023-07-04","cited_by_count":148},{"id":"2011.07057","title":"Learning to Drop: Robust Graph Neural Network via Topological Denoising","created":"2020-11-13","cited_by_count":127},{"id":"2102.06790","title":"A Unified Lottery Ticket Hypothesis for Graph Neural Networks","created":"2021-02-12","cited_by_count":118},{"id":"2201.06367","title":"Towards Unsupervised Deep Graph Structure Learning","created":"2022-01-17","cited_by_count":114},{"id":"2202.08455","title":"Transformer for Graphs: An Overview from Architecture Perspective","created":"2022-02-17","cited_by_count":107},{"id":"2206.04216","title":"Neo-GNNs: Neighborhood Overlap-aware Graph Neural Networks for Link Prediction","created":"2022-06-09","cited_by_count":78},{"id":"2005.06870","title":"Dynamic Sparse Training: Find Efficient Sparse Network From Scratch With Trainable Masked Layers","created":"2020-05-14","cited_by_count":68},{"id":"2206.04674","title":"Uni-Perceiver-MoE: Learning Sparse Generalist Models with Conditional MoEs","created":"2022-06-09","cited_by_count":58},{"id":"2402.03358","title":"A Comprehensive Survey on Graph Reduction: Sparsification, Coarsening, and Condensation","created":"2024-01-29","cited_by_count":57},{"id":"2204.07321","title":"Graph Pooling for Graph Neural Networks: Progress, Challenges, and Opportunities","created":"2022-04-15","cited_by_count":52},{"id":"2310.05174","title":"GSLB: The Graph Structure Learning Benchmark","created":"2023-10-08","cited_by_count":50},{"id":"2006.15097","title":"Policy-GNN: Aggregation Optimization for Graph Neural Networks","created":"2020-06-26","cited_by_count":48},{"id":"2103.13355","title":"Bag of Tricks for Node Classification with Graph Neural Networks","created":"2021-03-24","cited_by_count":40},{"id":"2108.10587","title":"Pooling Architecture Search for Graph Classification","created":"2021-08-24","cited_by_count":36},{"id":"1909.06940","title":"Multi-graph Fusion for Multi-view Spectral Clustering","created":"2019-09-16","cited_by_count":27},{"id":"2103.00794","title":"Early-Bird GCNs: Graph-Network Co-Optimization Towards More Efficient GCN Training and Inference via Drawing Early-Bird Lottery Tickets","created":"2021-03-01","cited_by_count":27},{"id":"2212.11440","title":"Self-supervised Hypergraph Representation Learning for Sociological Analysis","created":"2022-12-22","cited_by_count":27},{"id":"2305.13997","title":"Learning Subpocket Prototypes for Generalizable Structure-based Drug Design","created":"2023-05-22","cited_by_count":25},{"id":"2305.02190","title":"Rethinking Graph Lottery Tickets: Graph Sparsity Matters","created":"2023-05-03","cited_by_count":23},{"id":"2102.01670","title":"Keep the Gradients Flowing: Using Gradient Flow to Study Sparse Network Optimization","created":"2021-02-02","cited_by_count":22},{"id":"2302.13693","title":"Learning Topology-Specific Experts for Molecular Property Prediction","created":"2023-02-27","cited_by_count":15},{"id":"2311.12314","title":"Demystifying Graph Sparsification Algorithms in Graph Properties Preservation","created":"2023-11-21","cited_by_count":14},{"id":"1303.2221","title":"Clustering on Multi-Layer Graphs via Subspace Analysis on Grassmann Manifolds","created":"2013-03-09","cited_by_count":13},{"id":"2308.10051","title":"The Snowflake Hypothesis: Training Deep GNN with One Node One Receptive field","created":"2023-08-19","cited_by_count":11},{"id":"1601.00286","title":"Structure-Preserving Sparsification Methods for Social Networks","created":"2016-01-03","cited_by_count":10},{"id":"2402.01242","title":"Two Heads Are Better Than One: Boosting Graph Sparse Training via Semantic and Topological Awareness","created":"2024-02-02","cited_by_count":10},{"id":"2308.02916","title":"Adversarial Erasing with Pruned Elements: Towards Better Graph Lottery Ticket","created":"2023-08-05","cited_by_count":5},{"id":"2402.01261","title":"TEDDY: Trimming Edges with Degree-based Discrimination strategY","created":"2024-02-02","cited_by_count":4},{"id":"2110.15891","title":"Friendly Cut Sparsifiers and Faster Gomory-Hu Trees","created":"2021-10-29","cited_by_count":1}],"next_cursor":null}