{"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":"1710.10903","title":"Graph Attention Networks","created":"2017-10-30","cited_by_count":8923},{"id":"1810.00826","title":"How Powerful are Graph Neural Networks?","created":"2018-10-01","cited_by_count":4393},{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"id":"2005.00687","title":"Open Graph Benchmark: Datasets for Machine Learning on Graphs","created":"2020-05-02","cited_by_count":2163},{"id":"1907.02893","title":"Invariant Risk Minimization","created":"2019-07-05","cited_by_count":1854},{"id":"2203.05482","title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","created":"2022-03-10","cited_by_count":1396},{"id":"2212.04089","title":"Editing Models with Task Arithmetic","created":"2022-12-08","cited_by_count":1120},{"id":"1612.03928","title":"Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer","created":"2016-12-12","cited_by_count":1077},{"id":"1804.04235","title":"Adafactor: Adaptive Learning Rates with Sublinear Memory Cost","created":"2018-04-11","cited_by_count":905},{"id":"2111.09832","title":"Merging Models with Fisher-Weighted Averaging","created":"2021-11-18","cited_by_count":621},{"id":"1909.13021","title":"Multi-scale Attributed Node Embedding","created":"2019-09-28","cited_by_count":548},{"id":"1912.08795","title":"Dreaming to Distill: Data-free Knowledge Transfer via DeepInversion","created":"2019-12-18","cited_by_count":423},{"id":"2310.02575","title":"AdaMerging: Adaptive Model Merging for Multi-Task Learning","created":"2023-10-04","cited_by_count":252},{"id":"2009.11848","title":"How Neural Networks Extrapolate: From Feedforward to Graph Neural Networks","created":"2020-09-24","cited_by_count":222},{"id":"2106.06607","title":"Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalization","created":"2021-06-11","cited_by_count":220},{"id":"2305.03053","title":"ZipIt! Merging Models from Different Tasks without Training","created":"2023-05-04","cited_by_count":179},{"id":"2110.07580","title":"Graph Condensation for Graph Neural Networks","created":"2021-10-14","cited_by_count":150},{"id":"2003.09772","title":"Invariant Rationalization","created":"2020-03-22","cited_by_count":131},{"id":"2006.07253","title":"Dynamic Model Pruning with Feedback","created":"2020-06-12","cited_by_count":125},{"id":"2204.03044","title":"Fusing finetuned models for better pretraining","created":"2022-04-06","cited_by_count":110},{"id":"2112.15089","title":"Causal Attention for Interpretable and Generalizable Graph Classification","created":"2021-12-30","cited_by_count":108},{"id":"2006.08195","title":"Neural Networks Fail to Learn Periodic Functions and How to Fix It","created":"2020-06-15","cited_by_count":100},{"id":"2010.02066","title":"Are Neural Nets Modular? Inspecting Functional Modularity Through Differentiable Weight Masks","created":"2020-10-05","cited_by_count":98},{"id":"2202.07987","title":"Out-Of-Distribution Generalization on Graphs: A Survey","created":"2022-02-16","cited_by_count":97},{"id":"2106.04496","title":"Towards a Theoretical Framework of Out-of-Distribution Generalization","created":"2021-06-08","cited_by_count":94},{"id":"2004.12406","title":"Masking as an Efficient Alternative to Finetuning for Pretrained Language Models","created":"2020-04-26","cited_by_count":93},{"id":"2407.04153","title":"Mixture of A Million Experts","created":"2024-07-04","cited_by_count":72},{"id":"2111.10657","title":"Generalizing Graph Neural Networks on Out-Of-Distribution Graphs","created":"2021-11-20","cited_by_count":71},{"id":"2203.06714","title":"A Survey on Deep Graph Generation: Methods and Applications","created":"2022-03-13","cited_by_count":69},{"id":"2304.02806","title":"Graph Mixture of Experts: Learning on Large-Scale Graphs with Explicit Diversity Modeling","created":"2023-04-06","cited_by_count":64},{"id":"2206.13697","title":"Graph Condensation via Receptive Field Distribution Matching","created":"2022-06-28","cited_by_count":60},{"id":"2408.07057","title":"A Survey on Model MoErging: Recycling and Routing Among Specialized Experts for Collaborative Learning","created":"2024-08-13","cited_by_count":52},{"id":"2105.07519","title":"Graph-Free Knowledge Distillation for Graph Neural Networks","created":"2021-05-16","cited_by_count":46},{"id":"2310.19035","title":"Does Invariant Graph Learning via Environment Augmentation Learn Invariance?","created":"2023-10-29","cited_by_count":42},{"id":"2004.14129","title":"How fine can fine-tuning be? Learning efficient language models","created":"2020-04-24","cited_by_count":41},{"id":"2307.15967","title":"Graph Condensation for Inductive Node Representation Learning","created":"2023-07-29","cited_by_count":31},{"id":"2306.01103","title":"Joint Learning of Label and Environment Causal Independence for Graph Out-of-Distribution Generalization","created":"2023-06-01","cited_by_count":29},{"id":"2106.06788","title":"Learngene: From Open-World to Your Learning Task","created":"2021-06-12","cited_by_count":27},{"id":"2309.10773","title":"Semi-supervised Domain Adaptation in Graph Transfer Learning","created":"2023-09-19","cited_by_count":27},{"id":"2311.11114","title":"Environment-Aware Dynamic Graph Learning for Out-of-Distribution Generalization","created":"2023-11-18","cited_by_count":26},{"id":"2312.10988","title":"Graph Invariant Learning with Subgraph Co-mixup for Out-Of-Distribution Generalization","created":"2023-12-18","cited_by_count":18},{"id":"2402.16374","title":"Graph Learning under Distribution Shifts: A Comprehensive Survey on Domain Adaptation, Out-of-distribution, and Continual Learning","created":"2024-02-26","cited_by_count":18},{"id":"2410.19265","title":"A Survey of Deep Graph Learning under Distribution Shifts: from Graph Out-of-Distribution Generalization to Adaptation","created":"2024-10-25","cited_by_count":17},{"id":"2202.00796","title":"On Balancing Bias and Variance in Unsupervised Multi-Source-Free Domain Adaptation","created":"2022-02-01","cited_by_count":16},{"id":"2412.00315","title":"One Model for One Graph: A New Perspective for Pretraining with Cross-domain Graphs","created":"2024-11-30","cited_by_count":12},{"id":"2306.08076","title":"Graph Structure and Feature Extrapolation for Out-of-Distribution Generalization","created":"2023-06-13","cited_by_count":10},{"id":"2308.08344","title":"Graph Out-of-Distribution Generalization with Controllable Data Augmentation","created":"2023-08-16","cited_by_count":9},{"id":"2410.16606","title":"GALA: Graph Diffusion-based Alignment with Jigsaw for Source-free Domain Adaptation","created":"2024-10-22","cited_by_count":8},{"id":"2505.16860","title":"GCAL: Adapting Graph Models to Evolving Domain Shifts","created":"2025-05-22","cited_by_count":8},{"id":"2205.03811","title":"Data-Free Adversarial Knowledge Distillation for Graph Neural Networks","created":"2022-05-08","cited_by_count":7},{"id":"2307.15049","title":"Regularized Mask Tuning: Uncovering Hidden Knowledge in Pre-trained Vision-Language Models","created":"2023-07-27","cited_by_count":7},{"id":"2311.05185","title":"Mixture of Weak & Strong Experts on Graphs","created":"2023-11-09","cited_by_count":7},{"id":"2403.05062","title":"Agile Multi-Source-Free Domain Adaptation","created":"2024-03-08","cited_by_count":7},{"id":"2406.07413","title":"Towards Continuous Reuse of Graph Models via Holistic Memory Diversification","created":"2024-06-11","cited_by_count":7},{"id":"2408.04400","title":"DIVE: Subgraph Disagreement for Graph Out-of-Distribution Generalization","created":"2024-08-08","cited_by_count":7},{"id":"2408.12185","title":"Rank and Align: Towards Effective Source-free Graph Domain Adaptation","created":"2024-08-22","cited_by_count":7},{"id":"2403.05523","title":"Beyond Finite Data: Towards Data-free Out-of-distribution Generalization via Extrapolation","created":"2024-03-08","cited_by_count":4}],"next_cursor":null}