{"total":129,"rows":[{"id":"2105.14491","title":"How Attentive are Graph Attention Networks?","created":"2021-05-30","cited_by_count":835,"area":null},{"id":"2305.11627","title":"LLM-Pruner: On the Structural Pruning of Large Language Models","created":"2023-05-19","cited_by_count":650,"area":null},{"id":"2210.08823","title":"Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuning","created":"2022-10-17","cited_by_count":294,"area":null},{"id":"2301.12900","title":"DepGraph: Towards Any Structural Pruning","created":"2023-01-30","cited_by_count":203,"area":null},{"id":"2206.00272","title":"Vision GNN: An Image is Worth Graph of Nodes","created":"2022-06-01","cited_by_count":186,"area":null},{"id":"2110.08727","title":"Graph-less Neural Networks: Teaching Old MLPs New Tricks via Distillation","created":"2021-10-17","cited_by_count":152,"area":null},{"id":"2211.17106","title":"Diffusion Probabilistic Model Made Slim","created":"2022-11-27","cited_by_count":121,"area":"diffusion"},{"id":"2210.16774","title":"Dataset Distillation via Factorization","created":"2022-10-30","cited_by_count":115,"area":null},{"id":"2303.10876","title":"EqMotion: Equivariant Multi-agent Motion Prediction with Invariant Interaction Reasoning","created":"2023-03-20","cited_by_count":97,"area":null},{"id":"2308.10916","title":"Diffusion Model as Representation Learner","created":"2023-08-21","cited_by_count":95,"area":"diffusion"},{"id":"2205.07424","title":"Trustworthy Graph Neural Networks: Aspects, Methods and Trends","created":"2022-05-16","cited_by_count":89,"area":null},{"id":"2210.17409","title":"Deep Model Reassembly","created":"2022-10-24","cited_by_count":78,"area":null},{"id":"2103.02885","title":"Extract the Knowledge of Graph Neural Networks and Go Beyond it: An Effective Knowledge Distillation Framework","created":"2021-03-04","cited_by_count":69,"area":"distill"},{"id":"2309.13625","title":"GraphAdapter: Tuning Vision-Language Models With Dual Knowledge Graph","created":"2023-09-24","cited_by_count":69,"area":"mllm"},{"id":"2105.08584","title":"Contrastive Model Inversion for Data-Free Knowledge Distillation","created":"2021-05-18","cited_by_count":66,"area":"distill"},{"id":"2207.03337","title":"Factorizing Knowledge in Neural Networks","created":"2022-07-04","cited_by_count":59,"area":null},{"id":"2206.06293","title":"Learning Domain Adaptive Object Detection with Probabilistic Teacher","created":"2022-06-13","cited_by_count":57,"area":null},{"id":"2105.07519","title":"Graph-Free Knowledge Distillation for Graph Neural Networks","created":"2021-05-16","cited_by_count":46,"area":"distill"},{"id":"2103.05872","title":"Sampling methods for efficient training of graph convolutional networks: A survey","created":"2021-03-10","cited_by_count":40,"area":null},{"id":"2210.05801","title":"Linkless Link Prediction via Relational Distillation","created":"2022-10-11","cited_by_count":39,"area":null},{"id":"2111.04964","title":"On Representation Knowledge Distillation for Graph Neural Networks","created":"2021-11-09","cited_by_count":38,"area":"distill"},{"id":"2302.00219","title":"Knowledge Distillation on Graphs: A Survey","created":"2023-02-01","cited_by_count":38,"area":"distill"},{"id":"2106.03772","title":"Learning Dynamics via Graph Neural Networks for Human Pose Estimation and Tracking","created":"2021-06-07","cited_by_count":37,"area":null},{"id":"2103.08357","title":"Learning Frequency-aware Dynamic Network for Efficient Super-Resolution","created":"2021-03-15","cited_by_count":36,"area":null},{"id":"2112.09445","title":"Data Efficient Language-supervised Zero-shot Recognition with Optimal Transport Distillation","created":"2021-12-17","cited_by_count":36,"area":null},{"id":"2105.11099","title":"Federated Graph Learning -- A Position Paper","created":"2021-05-24","cited_by_count":35,"area":null},{"id":"2308.02117","title":"VQGraph: Rethinking Graph Representation Space for Bridging GNNs and MLPs","created":"2023-08-04","cited_by_count":35,"area":"distill"},{"id":"2110.15094","title":"Mosaicking to Distill: Knowledge Distillation from Out-of-Domain Data","created":"2021-10-27","cited_by_count":32,"area":"distill"},{"id":"2106.02898","title":"Dynamic Resolution Network","created":"2021-06-05","cited_by_count":31,"area":null},{"id":"2112.03587","title":"TCGL: Temporal Contrastive Graph for Self-supervised Video Representation Learning","created":"2021-12-07","cited_by_count":31,"area":null},{"id":"2207.08224","title":"Learning with Recoverable Forgetting","created":"2022-07-17","cited_by_count":30,"area":null},{"id":"2207.11681","title":"Learning Graph Neural Networks for Image Style Transfer","created":"2022-07-24","cited_by_count":29,"area":null},{"id":"2210.04206","title":"Attention Diversification for Domain Generalization","created":"2022-10-09","cited_by_count":29,"area":null},{"id":"2304.10668","title":"Train Your Own GNN Teacher: Graph-Aware Distillation on Textual Graphs","created":"2023-04-20","cited_by_count":29,"area":null},{"id":"2202.04822","title":"Survey on Graph Neural Network Acceleration: An Algorithmic Perspective","created":"2022-02-10","cited_by_count":26,"area":null},{"id":"2206.04361","title":"Model Degradation Hinders Deep Graph Neural Networks","created":"2022-06-09","cited_by_count":26,"area":null},{"id":"2308.04268","title":"Teacher-Student Architecture for Knowledge Distillation: A Survey","created":"2023-08-08","cited_by_count":26,"area":"distill"},{"id":"2109.12872","title":"Meta-Aggregator: Learning to Aggregate for 1-bit Graph Neural Networks","created":"2021-09-27","cited_by_count":25,"area":null},{"id":"2203.15625","title":"PoseTriplet: Co-evolving 3D Human Pose Estimation, Imitation, and Hallucination under Self-supervision","created":"2022-03-29","cited_by_count":25,"area":null},{"id":"2306.05628","title":"Quantifying the Knowledge in GNNs for Reliable Distillation into MLPs","created":"2023-06-09","cited_by_count":25,"area":"distill"},{"id":"2207.06124","title":"DynaST: Dynamic Sparse Transformer for Exemplar-Guided Image Generation","created":"2022-07-13","cited_by_count":24,"area":null},{"id":"2206.06561","title":"FreeKD: Free-direction Knowledge Distillation for Graph Neural Networks","created":"2022-06-14","cited_by_count":23,"area":"distill"},{"id":"2210.13014","title":"Geometric Knowledge Distillation: Topology Compression for Graph Neural Networks","created":"2022-10-24","cited_by_count":22,"area":"distill"},{"id":"2304.14593","title":"Deep Graph Reprogramming","created":"2023-04-28","cited_by_count":22,"area":null},{"id":"2310.04987","title":"Data-centric Graph Learning: A Survey","created":"2023-10-08","cited_by_count":22,"area":null},{"id":"2308.08942","title":"Auxiliary Tasks Benefit 3D Skeleton-based Human Motion Prediction","created":"2023-08-17","cited_by_count":20,"area":null},{"id":"2106.15941","title":"Augmented Shortcuts for Vision Transformers","created":"2021-06-30","cited_by_count":19,"area":null},{"id":"2204.02547","title":"Modeling Motion with Multi-Modal Features for Text-Based Video Segmentation","created":"2022-04-06","cited_by_count":18,"area":null},{"id":"2205.11678","title":"Compressing Deep Graph Neural Networks via Adversarial Knowledge Distillation","created":"2022-05-24","cited_by_count":18,"area":"distill"},{"id":"2207.08629","title":"Comprehensive Graph Gradual Pruning for Sparse Training in Graph Neural Networks","created":"2022-07-18","cited_by_count":18,"area":null},{"id":"2303.10139","title":"Distill n' Explain: explaining graph neural networks using simple surrogates","created":"2023-03-17","cited_by_count":18,"area":null},{"id":"2306.14052","title":"A Survey on Graph Neural Network Acceleration: Algorithms, Systems, and Customized Hardware","created":"2023-06-24","cited_by_count":18,"area":null},{"id":"2406.01032","title":"LLM and GNN are Complementary: Distilling LLM for Multimodal Graph Learning","created":"2024-06-03","cited_by_count":17,"area":"distill"},{"id":"2302.02922","title":"Joint Edge-Model Sparse Learning is Provably Efficient for Graph Neural Networks","created":"2023-02-06","cited_by_count":16,"area":null},{"id":"2304.11595","title":"Segment Anything in Non-Euclidean Domains: Challenges and Opportunities","created":"2023-04-23","cited_by_count":16,"area":null},{"id":"2203.13394","title":"Point2Seq: Detecting 3D Objects as Sequences","created":"2022-03-25","cited_by_count":15,"area":null},{"id":"2207.02375","title":"3DG-STFM: 3D Geometric Guided Student-Teacher Feature Matching","created":"2022-07-06","cited_by_count":14,"area":null},{"id":"2208.10010","title":"NOSMOG: Learning Noise-robust and Structure-aware MLPs on Graphs","created":"2022-08-22","cited_by_count":14,"area":null},{"id":"2210.05920","title":"Boosting Graph Neural Networks via Adaptive Knowledge Distillation","created":"2022-10-12","cited_by_count":14,"area":"distill"},{"id":"2402.05894","title":"Large Language Model Meets Graph Neural Network in Knowledge Distillation","created":"2024-02-08","cited_by_count":14,"area":"distill"},{"id":"2109.14960","title":"Prune Your Model Before Distill It","created":"2021-09-30","cited_by_count":12,"area":"distill"},{"id":"2210.09609","title":"SA-MLP: Distilling Graph Knowledge from GNNs into Structure-Aware MLP","created":"2022-10-18","cited_by_count":12,"area":"distill"},{"id":"2105.04181","title":"KDExplainer: A Task-oriented Attention Model for Explaining Knowledge Distillation","created":"2021-05-10","cited_by_count":11,"area":"distill"},{"id":"2306.14818","title":"Accelerating Molecular Graph Neural Networks via Knowledge Distillation","created":"2023-06-26","cited_by_count":11,"area":"distill"},{"id":"2112.03695","title":"Safe Distillation Box","created":"2021-12-05","cited_by_count":9,"area":"distill"},{"id":"2206.06620","title":"Slimmable Domain Adaptation","created":"2022-06-14","cited_by_count":9,"area":null},{"id":"2308.13982","title":"Universal Graph Continual Learning","created":"2023-08-27","cited_by_count":9,"area":null},{"id":"2310.10998","title":"Accelerating Scalable Graph Neural Network Inference with Node-Adaptive Propagation","created":"2023-10-17","cited_by_count":8,"area":"inference"},{"id":"2403.03483","title":"A Teacher-Free Graph Knowledge Distillation Framework with Dual Self-Distillation","created":"2024-03-06","cited_by_count":8,"area":"distill"},{"id":"2211.00495","title":"Efficient Graph Neural Network Inference at Large Scale","created":"2022-11-01","cited_by_count":7,"area":"inference"},{"id":"2103.00430","title":"Training Generative Adversarial Networks in One Stage","created":"2021-02-28","cited_by_count":6,"area":null},{"id":"2210.02097","title":"Teaching Yourself: Graph Self-Distillation on Neighborhood for Node Classification","created":"2022-10-05","cited_by_count":6,"area":"distill"},{"id":"2302.14643","title":"Graph-based Knowledge Distillation: A survey and experimental evaluation","created":"2023-02-27","cited_by_count":6,"area":"distill"},{"id":"2303.10597","title":"Partial Network Cloning","created":"2023-03-19","cited_by_count":6,"area":null},{"id":"2405.14307","title":"AdaGMLP: AdaBoosting GNN-to-MLP Knowledge Distillation","created":"2024-05-23","cited_by_count":6,"area":"distill"},{"id":"2409.06748","title":"EasyST: A Simple Framework for Spatio-Temporal Prediction","created":"2024-09-10","cited_by_count":6,"area":null},{"id":"2103.09468","title":"Learning with Group Noise","created":"2021-03-17","cited_by_count":5,"area":null},{"id":"2205.02468","title":"Alignahead: Online Cross-Layer Knowledge Extraction on Graph Neural Networks","created":"2022-05-05","cited_by_count":5,"area":"distill"},{"id":"2207.11789","title":"Hierarchical Semi-Supervised Contrastive Learning for Contamination-Resistant Anomaly Detection","created":"2022-07-24","cited_by_count":5,"area":null},{"id":"2208.00817","title":"DSLA: Dynamic smooth label assignment for efficient anchor-free object detection","created":"2022-08-01","cited_by_count":5,"area":null},{"id":"2303.00613","title":"Diffusing Graph Attention","created":"2023-03-01","cited_by_count":5,"area":null},{"id":"2412.11180","title":"TINED: GNNs-to-MLPs by Teacher Injection and Dirichlet Energy Distillation","created":"2024-12-15","cited_by_count":5,"area":null},{"id":"2510.08962","title":"Analytical Survey of Learning with Low-Resource Data: From Analysis to Investigation","created":"2025-10-10","cited_by_count":5,"area":null},{"id":"2407.14768","title":"Teach Harder, Learn Poorer: Rethinking Hard Sample Distillation for GNN-to-MLP Knowledge Distillation","created":"2024-07-20","cited_by_count":4,"area":"distill"},{"id":"2502.19252","title":"GraphBridge: Towards Arbitrary Transfer Learning in GNNs","created":"2025-02-26","cited_by_count":4,"area":null},{"id":"2205.12583","title":"MUG: Multi-human Graph Network for 3D Mesh Reconstruction from 2D Pose","created":"2022-05-25","cited_by_count":3,"area":null},{"id":"2304.00502","title":"CNNs with Multi-Level Attention for Domain Generalization","created":"2023-04-02","cited_by_count":3,"area":null},{"id":"2312.05479","title":"Exploring Sparsity in Graph Transformers","created":"2023-12-09","cited_by_count":3,"area":null},{"id":"2312.09086","title":"COMBHelper: A Neural Approach to Reduce Search Space for Graph Combinatorial Problems","created":"2023-12-14","cited_by_count":3,"area":null},{"id":"2407.15320","title":"Edge Graph Intelligence: Reciprocally Empowering Edge Networks with Graph Intelligence","created":"2024-07-07","cited_by_count":3,"area":null},{"id":"2505.09361","title":"Efficient Mixed Precision Quantization in Graph Neural Networks","created":"2025-05-14","cited_by_count":3,"area":null},{"id":"2507.02911","title":"DiceHuBERT: Distilling HuBERT with a Self-Supervised Learning Objective","created":"2025-06-25","cited_by_count":3,"area":"distill"},{"id":"2508.02801","title":"Adaptive Knowledge Distillation for Device-Directed Speech Detection","created":"2025-08-04","cited_by_count":3,"area":"distill"},{"id":"2108.01075","title":"Boundary Knowledge Translation based Reference Semantic Segmentation","created":"2021-08-01","cited_by_count":2,"area":null},{"id":"2110.06290","title":"Scalable Consistency Training for Graph Neural Networks via Self-Ensemble Self-Distillation","created":"2021-10-12","cited_by_count":2,"area":"distill"},{"id":"2112.06253","title":"Up to 100$\\times$ Faster Data-free Knowledge Distillation","created":"2021-12-12","cited_by_count":2,"area":"distill"},{"id":"2205.14938","title":"Spectral Maps for Learning on Subgraphs","created":"2022-05-30","cited_by_count":2,"area":null},{"id":"2207.11887","title":"HIRE: Distilling High-order Relational Knowledge From Heterogeneous Graph Neural Networks","created":"2022-07-25","cited_by_count":2,"area":"distill"},{"id":"2210.03900","title":"Bottleneck Analysis of Dynamic Graph Neural Network Inference on CPU and GPU","created":"2022-10-08","cited_by_count":2,"area":null},{"id":"2307.06631","title":"Frameless Graph Knowledge Distillation","created":"2023-07-13","cited_by_count":2,"area":"distill"}],"next_cursor":"100"}