{"total":96,"rows":[{"id":"2103.13630","title":"A Survey of Quantization Methods for Efficient Neural Network Inference","created":"2021-03-25","cited_by_count":815,"area":null},{"id":"2308.07633","title":"A Survey on Model Compression for Large Language Models","created":"2023-08-15","cited_by_count":269,"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":"2102.06790","title":"A Unified Lottery Ticket Hypothesis for Graph Neural Networks","created":"2021-02-12","cited_by_count":118,"area":null},{"id":"2205.07424","title":"Trustworthy Graph Neural Networks: Aspects, Methods and Trends","created":"2022-05-16","cited_by_count":89,"area":null},{"id":"2111.05193","title":"A Survey on Green Deep Learning","created":"2021-11-08","cited_by_count":52,"area":null},{"id":"2110.14363","title":"VQ-GNN: A Universal Framework to Scale up Graph Neural Networks using Vector Quantization","created":"2021-10-27","cited_by_count":39,"area":null},{"id":"2111.06061","title":"Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AI","created":"2021-11-11","cited_by_count":39,"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":"2411.02530","title":"A Comprehensive Study on Quantization Techniques for Large Language Models","created":"2024-10-30","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":"2211.00216","title":"Distributed Graph Neural Network Training: A Survey","created":"2022-11-01","cited_by_count":32,"area":null},{"id":"2307.15967","title":"Graph Condensation for Inductive Node Representation Learning","created":"2023-07-29","cited_by_count":31,"area":null},{"id":"2202.05239","title":"F8Net: Fixed-Point 8-bit Only Multiplication for Network Quantization","created":"2022-02-10","cited_by_count":28,"area":null},{"id":"2406.12930","title":"Tender: Accelerating Large Language Models via Tensor Decomposition and Runtime Requantization","created":"2024-06-16","cited_by_count":28,"area":null},{"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,"area":null},{"id":"2402.05147","title":"ApiQ: Finetuning of 2-Bit Quantized Large Language Model","created":"2024-02-07","cited_by_count":27,"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":"2311.06322","title":"Post-training Quantization for Text-to-Image Diffusion Models with Progressive Calibration and Activation Relaxing","created":"2023-11-10","cited_by_count":21,"area":"diffusion"},{"id":"2402.01799","title":"Faster and Lighter LLMs: A Survey on Current Challenges and Way Forward","created":"2024-02-02","cited_by_count":21,"area":null},{"id":"2111.09547","title":"QGTC: Accelerating Quantized Graph Neural Networks via GPU Tensor Core","created":"2021-11-18","cited_by_count":18,"area":null},{"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":"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":"2403.02775","title":"EasyQuant: An Efficient Data-free Quantization Algorithm for LLMs","created":"2024-03-05","cited_by_count":17,"area":null},{"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":"2310.09499","title":"One-Shot Sensitivity-Aware Mixed Sparsity Pruning for Large Language Models","created":"2023-10-14","cited_by_count":16,"area":null},{"id":"2109.08983","title":"G-CoS: GNN-Accelerator Co-Search Towards Both Better Accuracy and Efficiency","created":"2021-09-18","cited_by_count":15,"area":null},{"id":"2305.06559","title":"Patch-wise Mixed-Precision Quantization of Vision Transformer","created":"2023-05-11","cited_by_count":15,"area":null},{"id":"2305.13854","title":"The Evolution of Distributed Systems for Graph Neural Networks and their Origin in Graph Processing and Deep Learning: A Survey","created":"2023-05-23","cited_by_count":14,"area":null},{"id":"2112.11594","title":"GCoD: Graph Convolutional Network Acceleration via Dedicated Algorithm and Accelerator Co-Design","created":"2021-12-22","cited_by_count":13,"area":null},{"id":"2203.14642","title":"SPIQ: Data-Free Per-Channel Static Input Quantization","created":"2022-03-28","cited_by_count":12,"area":null},{"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":"2505.05530","title":"Low-bit Model Quantization for Deep Neural Networks: A Survey","created":"2025-05-08","cited_by_count":11,"area":null},{"id":"2203.13483","title":"MKQ-BERT: Quantized BERT with 4-bits Weights and Activations","created":"2022-03-25","cited_by_count":10,"area":null},{"id":"2306.01381","title":"Adaptive Message Quantization and Parallelization for Distributed Full-graph GNN Training","created":"2023-06-02","cited_by_count":10,"area":null},{"id":"2601.14888","title":"What Makes Low-Bit Quantization-Aware Training Work for Reasoning LLMs? A Systematic Study","created":"2026-01-21","cited_by_count":10,"area":"lr"},{"id":"2108.06317","title":"Towards Efficient Point Cloud Graph Neural Networks Through Architectural Simplification","created":"2021-08-13","cited_by_count":9,"area":null},{"id":"2311.15772","title":"Attend Who is Weak: Enhancing Graph Condensation via Cross-Free Adversarial Training","created":"2023-11-27","cited_by_count":9,"area":null},{"id":"2505.11892","title":"Fast RoPE Attention: Combining the Polynomial Method and Fast Fourier Transform","created":"2025-05-17","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":"2211.00495","title":"Efficient Graph Neural Network Inference at Large Scale","created":"2022-11-01","cited_by_count":7,"area":"inference"},{"id":"2303.12341","title":"EasyDGL: Encode, Train and Interpret for Continuous-time Dynamic Graph Learning","created":"2023-03-22","cited_by_count":7,"area":null},{"id":"2505.05215","title":"Diffusion Model Quantization: A Review","created":"2025-05-08","cited_by_count":6,"area":"diffusion"},{"id":"2110.04824","title":"Haar Wavelet Feature Compression for Quantized Graph Convolutional Networks","created":"2021-10-10","cited_by_count":5,"area":null},{"id":"2308.02916","title":"Adversarial Erasing with Pruned Elements: Towards Better Graph Lottery Ticket","created":"2023-08-05","cited_by_count":5,"area":null},{"id":"2308.14949","title":"Low-bit Quantization for Deep Graph Neural Networks with Smoothness-aware Message Propagation","created":"2023-08-29","cited_by_count":5,"area":null},{"id":"2207.14696","title":"BiFeat: Supercharge GNN Training via Graph Feature Quantization","created":"2022-07-29","cited_by_count":4,"area":null},{"id":"2208.03559","title":"Triple Sparsification of Graph Convolutional Networks without Sacrificing the Accuracy","created":"2022-08-06","cited_by_count":4,"area":null},{"id":"2308.00890","title":"Tango: rethinking quantization for graph neural network training on GPUs","created":"2023-08-02","cited_by_count":4,"area":null},{"id":"2309.17341","title":"MixQuant: Mixed Precision Quantization with a Bit-width Optimization Search","created":"2023-09-29","cited_by_count":4,"area":null},{"id":"2311.09775","title":"MEGA: A Memory-Efficient GNN Accelerator Exploiting Degree-Aware Mixed-Precision Quantization","created":"2023-11-16","cited_by_count":4,"area":null},{"id":"2111.03184","title":"LW-GCN: A Lightweight FPGA-based Graph Convolutional Network Accelerator","created":"2021-11-04","cited_by_count":3,"area":null},{"id":"2302.13438","title":"P4L: Privacy Preserving Peer-to-Peer Learning for Infrastructureless Setups","created":"2023-02-26","cited_by_count":3,"area":null},{"id":"2303.01277","title":"Boosting Distributed Full-graph GNN Training with Asynchronous One-bit Communication","created":"2023-03-02","cited_by_count":3,"area":null},{"id":"2403.17154","title":"On the Impact of Black-box Deployment Strategies for Edge AI on Latency and Model Performance","created":"2024-03-25","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":"2301.07266","title":"ACQ: Improving Generative Data-free Quantization Via Attention Correction","created":"2023-01-18","cited_by_count":2,"area":null},{"id":"2306.11800","title":"Inshrinkerator: Compressing Deep Learning Training Checkpoints via Dynamic Quantization","created":"2023-06-20","cited_by_count":2,"area":null},{"id":"2307.01684","title":"Serving Graph Neural Networks With Distributed Fog Servers For Smart IoT Services","created":"2023-07-04","cited_by_count":2,"area":null},{"id":"2307.06631","title":"Frameless Graph Knowledge Distillation","created":"2023-07-13","cited_by_count":2,"area":"distill"},{"id":"2312.03236","title":"Multicoated and Folded Graph Neural Networks with Strong Lottery Tickets","created":"2023-12-06","cited_by_count":2,"area":null},{"id":"2410.20046","title":"DQRM: Deep Quantized Recommendation Models","created":"2024-10-26","cited_by_count":2,"area":null},{"id":"2412.20796","title":"FastCHGNet: Training one Universal Interatomic Potential to 1.5 Hours with 32 GPUs","created":"2024-12-30","cited_by_count":2,"area":null},{"id":"2511.18474","title":"Adaptive Mesh-Quantization for Neural PDE Solvers","created":"2025-11-23","cited_by_count":2,"area":null},{"id":"2603.04545","title":"An LLM-Guided Query-Aware Inference System for GNN Models on Large Knowledge Graphs","created":"2026-03-04","cited_by_count":2,"area":null},{"id":"2403.02243","title":"Better Schedules for Low Precision Training of Deep Neural Networks","created":"2024-03-04","cited_by_count":1,"area":null},{"id":"2408.13925","title":"Infrared Domain Adaptation with Zero-Shot Quantization","created":"2024-08-25","cited_by_count":1,"area":null},{"id":"2411.00907","title":"On the Impact of White-box Deployment Strategies for Edge AI on Latency and Model Performance","created":"2024-11-01","cited_by_count":1,"area":null},{"id":"2411.02926","title":"Privacy-Preserving Graph-Based Machine Learning with Fully Homomorphic Encryption for Collaborative Anti-Money Laundering","created":"2024-11-05","cited_by_count":1,"area":null},{"id":"2501.18154","title":"Mixed-Precision Graph Neural Quantization for Low Bit Large Language Models","created":"2025-01-30","cited_by_count":1,"area":null},{"id":"2502.21196","title":"AMPLE: Event-Driven Accelerator for Mixed-Precision Inference of Graph Neural Networks","created":"2025-02-28","cited_by_count":1,"area":null},{"id":"2507.04456","title":"BiVM: Accurate Binarized Neural Network for Efficient Video Matting","created":"2025-07-06","cited_by_count":1,"area":null},{"id":"2602.18227","title":"Parameter-Efficient Domain Adaptation of Physics-Informed Self-Attention based GNNs for AC Power Flow Prediction","created":"2026-02-20","cited_by_count":1,"area":null},{"id":"2604.10091","title":"SEPTQ: A Simple and Effective Post-Training Quantization Paradigm for Large Language Models","created":"2026-04-11","cited_by_count":1,"area":null},{"id":"2101.01163","title":"SmartDeal: Re-Modeling Deep Network Weights for Efficient Inference and Training","created":"2021-01-04","cited_by_count":0,"area":null},{"id":"2311.01205","title":"Attacking Graph Neural Networks with Bit Flips: Weisfeiler and Lehman Go Indifferent","created":"2023-11-02","cited_by_count":0,"area":null},{"id":"2403.01079","title":"Teaching MLP More Graph Information: A Three-stage Multitask Knowledge Distillation Framework","created":"2024-03-02","cited_by_count":0,"area":"distill"},{"id":"2405.04114","title":"Acceleration Algorithms in GNNs: A Survey","created":"2024-05-07","cited_by_count":0,"area":null},{"id":"2406.04456","title":"Learning Optimal Linear Precoding for Cell-Free Massive MIMO with GNN","created":"2024-06-06","cited_by_count":0,"area":null},{"id":"2406.17611","title":"Distributed Training of Large Graph Neural Networks with Variable Communication Rates","created":"2024-06-25","cited_by_count":0,"area":null},{"id":"2407.02805","title":"Efficient DNN-Powered Software with Fair Sparse Models","created":"2024-07-03","cited_by_count":0,"area":null},{"id":"2412.07605","title":"Fast Track to Winning Tickets: Repowering One-Shot Pruning for Graph Neural Networks","created":"2024-12-10","cited_by_count":0,"area":null},{"id":"2504.06193","title":"Heuristic Methods are Good Teachers to Distill MLPs for Graph Link Prediction","created":"2025-04-08","cited_by_count":0,"area":"distill"},{"id":"2504.13034","title":"Inference-friendly Graph Compression for Graph Neural Networks","created":"2025-04-17","cited_by_count":0,"area":null},{"id":"2509.26277","title":"Cat: Post-Training Quantization Error Reduction via Cluster-based Affine Transformation","created":"2025-09-30","cited_by_count":0,"area":null},{"id":"2510.22058","title":"Pruning and Quantization Impact on Graph Neural Networks","created":"2025-10-24","cited_by_count":0,"area":null},{"id":"2511.03201","title":"A Quantized VAE-MLP Botnet Detection Model: A Systematic Evaluation of Quantization-Aware Training and Post-Training Quantization Strategies","created":"2025-11-05","cited_by_count":0,"area":null},{"id":"2601.02213","title":"Quantized SO(3)-Equivariant Graph Neural Networks for Efficient Molecular Property Prediction","created":"2026-01-05","cited_by_count":0,"area":null},{"id":"2602.19017","title":"Why ReLU? A Bit-Model Dichotomy for Deep Network Training","created":"2026-02-22","cited_by_count":0,"area":null},{"id":"2602.20646","title":"On the Convergence of Stochastic Gradient Descent with Perturbed Forward-Backward Passes","created":"2026-02-24","cited_by_count":0,"area":null},{"id":"2603.05343","title":"Preserving Continuous Symmetry in Discrete Spaces: Geometric-Aware Quantization for SO(3)-Equivariant GNNs","created":"2026-03-05","cited_by_count":0,"area":null},{"id":"2608.29667","title":"A Target-Centric Survey of Quantization-Aware Training","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2608.30394","title":"TopGQ: Fast GNN Post-Training Quantization Leveraging Topology Information","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2610.15092","title":"VLCQ: Post-training quantization for deep neural networks using variable length coding","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}