Pith. sign in

REVIEW 14 cited by

SIGN: Scalable Inception Graph Neural Networks

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2004.11198 v3 pith:MKOUJY4I submitted 2020-04-23 cs.LG stat.ML

SIGN: Scalable Inception Graph Neural Networks

classification cs.LG stat.ML
keywords graphnetworkstrainingarchitecturedifferentefficientinferencelearning
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Graph representation learning has recently been applied to a broad spectrum of problems ranging from computer graphics and chemistry to high energy physics and social media. The popularity of graph neural networks has sparked interest, both in academia and in industry, in developing methods that scale to very large graphs such as Facebook or Twitter social networks. In most of these approaches, the computational cost is alleviated by a sampling strategy retaining a subset of node neighbors or subgraphs at training time. In this paper we propose a new, efficient and scalable graph deep learning architecture which sidesteps the need for graph sampling by using graph convolutional filters of different size that are amenable to efficient precomputation, allowing extremely fast training and inference. Our architecture allows using different local graph operators (e.g. motif-induced adjacency matrices or Personalized Page Rank diffusion matrix) to best suit the task at hand. We conduct extensive experimental evaluation on various open benchmarks and show that our approach is competitive with other state-of-the-art architectures, while requiring a fraction of the training and inference time. Moreover, we obtain state-of-the-art results on ogbn-papers100M, the largest public graph dataset, with over 110 million nodes and 1.5 billion edges.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 14 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. When does distribution shift break graph neural networks calibration?

    cs.LG 2026-07 conditional novelty 7.0

    GNN calibration under distribution shift is governed by a single closed-form slope κ(hs, ht, ρ) that sets the optimal global temperature T⋆=1/κ and explains when node-wise recalibration cannot help.

  2. Gate the Filter, Not the Message: Node-Channel Mixtures for Pre-Propagation GNNs

    cs.LG 2026-06 conditional novelty 7.0

    FilterMoE uses joint node-channel routing of Chebyshev filter experts through a 3D gating tensor in pre-propagation GNNs and outperforms baselines on nine of eleven benchmarks while ranking first on all three large-sc...

  3. Evaluating LLMs on Large-Scale Graph Property Estimation via Random Walks

    cs.LG 2026-05 unverdicted novelty 7.0

    EstGraph benchmark evaluates LLMs on estimating properties of very large graphs from random-walk samples that fit in context limits.

  4. Operational Feature Fingerprints of Graph Datasets via a White-Box Signal-Subspace Probe

    cs.LG 2026-04 unverdicted novelty 7.0

    WG-SRC is a white-box signal-subspace classifier that decomposes graph node classification into interpretable components to produce operational fingerprints distinguishing dataset behaviors like low-pass dominance or ...

  5. Temporal Graph Networks for Deep Learning on Dynamic Graphs

    cs.LG 2020-06 unverdicted novelty 7.0

    Temporal Graph Networks combine memory modules and graph operators to learn on dynamic graphs as timed event sequences, outperforming prior methods on transductive and inductive tasks while unifying earlier models as ...

  6. FedLAB: Traceable Semantic Codebooks for Federated Multimodal Graph Foundation Learning

    cs.LG 2026-06 unverdicted novelty 6.0

    FedLAB organizes multimodal graph knowledge into typed hierarchical codebooks for modality evidence, node semantics, and topology context via federated semantic barycenter pre-training, improving performance by up to ...

  7. TGHE: Template-based Graph Homomorphic Encryption for Privacy-Preserving GNN Inference in Edge-Cloud Systems

    cs.CR 2026-06 unverdicted novelty 6.0

    TGHE packs structurally identical ego-graph trees into shared CKKS ciphertexts for parallel encrypted GNN inference, delivering 66.9x speedup on a 3.7M-node financial graph with <0.002 AUC loss.

  8. Enhancing LLMs for Graph Tasks via Graph-aware LoRA Generation

    cs.LG 2026-06 unverdicted novelty 6.0

    GaRA generates task-specific LoRA weight updates conditioned on graph structures to enable better whole-graph encoding in LLMs for zero-shot graph learning.

  9. CAMPA: Efficient and Aligned Multimodal Graph Learning via Decoupled Propagation and Aggregation

    cs.AI 2026-05 unverdicted novelty 6.0

    CAMPA resolves modal conflicts in decoupled multimodal GNNs via cross-modal aligned propagation and trajectory aligned aggregation, outperforming coupled and decoupled baselines on benchmarks while retaining efficiency.

  10. Hierarchical Multi-Scale Graph Neural Networks: Scalable Heterophilous Learning with Oversmoothing and Oversquashing Mitigation

    cs.LG 2026-05 unverdicted novelty 6.0

    HMH builds soft hierarchies with orthonormal Haar bases and heterophily-aware encoders to apply learnable spectral filters while using skip unpooling to avoid oversmoothing and hub bias on heterophilous graphs.

  11. No Need to Train Your RDB Foundation Model

    cs.AI 2026-02 conditional novelty 6.0

    Column-wise, parameter-free JUICE encodings let single-table ICL models solve multi-table RDB prediction tasks with no training or fine-tuning.

  12. Revisiting Pre-Propagation GNNs: Robust Diffusion Operators and Hidden-State Re-Propagation

    cs.LG 2026-05 unverdicted novelty 5.0

    Robust diffusion operators and hidden-state re-propagation improve PPGNN accuracy to match message-passing GNNs on benchmarks.

  13. Efficiently Learning Branching Networks for Multitask Algorithmic Reasoning

    cs.LG 2025-11 conditional novelty 5.0

    AutoBRANE learns tree-structured branching networks for multitask algorithmic reasoning via gradient-based task affinities and convex relaxation.

  14. AdvSynGNN: Structure-Adaptive Graph Neural Nets via Adversarial Synthesis and Self-Corrective Propagation

    cs.LG 2026-02 unverdicted novelty 4.0

    AdvSynGNN uses multi-resolution structural synthesis, contrastive objectives, an adaptive transformer, and an adversarial propagation engine with residual label correction to improve node-level predictions on challeng...