Papers › LanczosNet: Multi-Scale Deep Graph Convolutional Networks

LanczosNet: Multi-Scale Deep Graph Convolutional Networks

6 Jan 2019ICLR 2019 5arXiv:1901.01484archive 2025-07-28

Renjie Liao, Zhizhen Zhao, Raquel Urtasun, Richard S. Zemel

We propose the Lanczos network (LanczosNet), which uses the Lanczos algorithm to construct low rank approximations of the graph Laplacian for graph convolution. Relying on the tridiagonal decomposition of the Lanczos algorithm, we not only efficiently exploit multi-scale information via fast approximated computation of matrix power but also design learnable spectral filters. Being fully differentiable, LanczosNet facilitates both graph kernel learning as well as learning node embeddings. We show the connection between our LanczosNet and graph based manifold learning methods, especially the diffusion maps. We benchmark our model against several recent deep graph networks on citation networks and QM8 quantum chemistry dataset. Experimental results show that our model achieves the state-of-the-art performance in most tasks. Code is released at: \url{https://github.com/lrjconan/LanczosNetwork}.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

lrjconan/LanczosNetwork officialmentioned in papermentioned on GitHubpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Node Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Node Classification CiteSeer (0.5%) AdaLanczosNet Accuracy 53.8 ± 4.7 #7 of 14 Archive leaderboard report
Node Classification CiteSeer (0.5%) LanczosNet Accuracy 53.2 ± 4.0 #8 of 14 Archive leaderboard report
Node Classification CiteSeer (1%) AdaLanczosNet Accuracy 63.3 ± 1.8 #7 of 14 Archive leaderboard report
Node Classification CiteSeer (1%) LanczosNet Accuracy 61.3 ± 3.9 #9 of 14 Archive leaderboard report
Node Classification CiteSeer with Public Split: fixed 20 nodes per class AdaLanczosNet Accuracy 68.7 ± 1.0 #35 of 40 Archive leaderboard report
Node Classification CiteSeer with Public Split: fixed 20 nodes per class LanczosNet Accuracy 66.2 ± 1.9 #37 of 40 Archive leaderboard report
Node Classification Cora (0.5%) AdaLanczosNet Accuracy 60.8 ± 9.0 #8 of 15 Archive leaderboard report
Node Classification Cora (0.5%) LanczosNet Accuracy 58.1 ± 8.2 #10 of 15 Archive leaderboard report
Node Classification Cora (1%) AdaLanczosNet Accuracy 67.5 ± 8.7 #8 of 15 Archive leaderboard report
Node Classification Cora (1%) LanczosNet Accuracy 66.1 ± 8.2 #10 of 15 Archive leaderboard report
Node Classification Cora (3%) AdaLanczosNet Accuracy 77.7 ± 2.4 #8 of 15 Archive leaderboard report
Node Classification Cora (3%) LanczosNet Accuracy 76.3 ± 2.3 #10 of 15 Archive leaderboard report
Node Classification Cora with Public Split: fixed 20 nodes per class AdaLanczosNet Accuracy 80.4 ± 1.1 #30 of 36 Archive leaderboard report
Node Classification Cora with Public Split: fixed 20 nodes per class LanczosNet Accuracy 79.5 ± 1.8 #32 of 36 Archive leaderboard report
Node Classification PubMed (0.03%) AdaLanczosNet Accuracy 61% #7 of 14 Archive leaderboard report
Node Classification PubMed (0.03%) LanczosNet Accuracy 60.4 ± 8.6 #9 of 14 Archive leaderboard report
Node Classification PubMed (0.05%) LanczosNet Accuracy 68.8 ± 5.6 #7 of 14 Archive leaderboard report
Node Classification PubMed (0.05%) AdaLanczosNet Accuracy 66% #9 of 14 Archive leaderboard report
Node Classification PubMed (0.1%) LanczosNet Accuracy 73.4 ± 5.1 #6 of 14 Archive leaderboard report
Node Classification PubMed (0.1%) AdaLanczosNet Accuracy 72.8 ± 4.6 #9 of 14 Archive leaderboard report
Node Classification PubMed with Public Split: fixed 20 nodes per class LanczosNet Accuracy 78.3 ± 0.3 #27 of 37 Archive leaderboard report
Node Classification PubMed with Public Split: fixed 20 nodes per class AdaLanczosNet Accuracy 78.1 ± 0.4 #28 of 37 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections