Node Classification On Citeseer
المقاييس
Accuracy
Validation
النتائج
نتائج أداء النماذج المختلفة على هذا المعيار القياسي
جدول المقارنة
| اسم النموذج | Accuracy | Validation |
|---|---|---|
| multi-task-graph-autoencoders | 71.80% | YES |
| predict-then-propagate-graph-neural-networks | 75.83% | YES |
| graph-optimized-convolutional-networks | 71.8% | - |
| snore-scalable-unsupervised-learning-of | 66.6 | - |
| splinecnn-fast-geometric-deep-learning-with | 79.20% | - |
| the-split-matters-flat-minima-methods-for | 77.99 ± 1.57% | - |
| is-heterophily-a-real-nightmare-for-graph | 81.56 ± 1.15 | - |
| learning-discrete-structures-for-graph-neural | 75.0 | - |
| learning-to-make-predictions-on-graphs-with | 71.60% | - |
| gresnet-graph-residuals-for-reviving-deep | 72.7% | - |
| fast-graph-representation-learning-with | 70.0 ± 1.4 | - |
| is-heterophily-a-real-nightmare-for-graph | 81.58 ± 1.23 | - |
| graph-representation-learning-beyond-node-and | 75.53 | - |
| beyond-homophily-structure-aware-path | - | - |
| gresnet-graph-residuals-for-reviving-deep | 73.5% | - |
| mitigating-degree-biases-in-message-passing | 76.59±0.98 | - |
| graphite-iterative-generative-modeling-of | 71.0 ± 0.07 | - |
| structure-fusion-based-on-graph-convolutional | 73.4% | - |
| hpgat-high-order-proximity-informed-graph | 73.0% | - |
| adagcn-adaboosting-graph-convolutional | 76.22 ± 0.20 | - |
| optimization-of-graph-neural-networks-with | 80.52 ± 0.14 | - |
| understanding-over-squashing-and-bottlenecks-1 | 72.58±0.20 | - |
| inferring-from-references-with-differences | 76.33 | - |
| measuring-and-relieving-the-over-smoothing | 69.7% | - |
| gresnet-graph-residuals-for-reviving-deep | 71.6% | - |
| just-jump-dynamic-neighborhood-aggregation-in | 74.50% | - |
| distilling-self-knowledge-from-contrastive | 75.79% | - |
| dfnets-spectral-cnns-for-graphs-with-feedback | 74.7 ± 0.4 | - |
| graph-trees-with-attention | 74.5 | - |
| distilling-self-knowledge-from-contrastive | 74.72% | - |
| get-rid-of-suspended-animation-problem-deep | 72.7% | - |
| transitivity-preserving-graph-representation | 76.08±2.5 | - |
| certifiable-robustness-and-robust-training | 68% | - |
| graph-adversarial-training-dynamically | 73.7% | - |
| graph-less-neural-networks-teaching-old-mlps-1 | 71.77± 2.01 | - |
| cleora-a-simple-strong-and-scalable-graph | 75.7 | - |
| distilling-self-knowledge-from-contrastive | 75.77% | - |
| distilling-self-knowledge-from-contrastive | 75.25% | - |
| deep-autoencoder-like-nonnegative-matrix | 42.42% | - |
| graph-attention-networks | 72.5 ± 0.7% | YES |
| is-heterophily-a-real-nightmare-for-graph | 81.68 ± 0.97 | - |
| graph-u-nets | 73.2 ± 0.5% | - |
| n-gcn-multi-scale-graph-convolution-for-semi | 72.2% | - |
| graphnas-graph-neural-architecture-search | 73.1 ± 0.9% | - |
| unifying-graph-convolutional-neural-networks-1 | 78.7 ± 0.6 | - |
| diffwire-inductive-graph-rewiring-via-the | 72.26 | - |
| graph-infoclust-leveraging-cluster-level-node | 71.9 ± 1.4 | - |
| tackling-oversmoothing-of-gnns-with-1 | 61.25±1.29 | - |
| multi-mask-aggregators-for-graph-neural | 76.30% | - |
| graph-bert-only-attention-is-needed-for | 71.2% | - |
| mixhop-higher-order-graph-convolution | 71.4% | YES |
| deep-graph-infomax | 71.8 ± 0.7% | - |
| large-scale-learnable-graph-convolutional | 73.0 ± 0.6% | - |
| graph-wavelet-neural-network-1 | 71.7% | - |
| predict-then-propagate-graph-neural-networks | 75.73% | - |
| diffwire-inductive-graph-rewiring-via-the | 66.71 | - |
| is-heterophily-a-real-nightmare-for-graph | 82.07 ± 1.04 | - |
| watch-your-step-learning-node-embeddings-via | 51.5% | - |
| a-flexible-generative-framework-for-graph | 74.5% | YES |
| nodenet-a-graph-regularised-neural-network | 80.09% | - |
| deep-graph-contrastive-representation | 72.1 ± 0.5 | - |
| structure-fusion-based-on-graph-convolutional | 73.5% | - |
| cn-motifs-perceptive-graph-neural-networks | 76.81±1.40 | - |
| gresnet-graph-residuals-for-reviving-deep | 73.7% | - |
| diffusion-improves-graph-learning-1 | 73.35% | - |
| semi-supervised-classification-with-graph | 70.3 | - |
| strong-transitivity-relations-and-graph | - | - |
| convolutional-neural-networks-on-graphs-with | 69.8% | - |
| graph-star-net-for-generalized-multi-task-1 | 71.0 | - |
| revisiting-semi-supervised-learning-with | 64.7% | - |