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
SIGN: Scalable Inception Graph Neural Networks
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.
Forward citations
Cited by 14 Pith papers
-
When does distribution shift break graph neural networks calibration?
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.
-
Gate the Filter, Not the Message: Node-Channel Mixtures for Pre-Propagation GNNs
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...
-
Evaluating LLMs on Large-Scale Graph Property Estimation via Random Walks
EstGraph benchmark evaluates LLMs on estimating properties of very large graphs from random-walk samples that fit in context limits.
-
Operational Feature Fingerprints of Graph Datasets via a White-Box Signal-Subspace Probe
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 ...
-
Temporal Graph Networks for Deep Learning on Dynamic Graphs
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 ...
-
FedLAB: Traceable Semantic Codebooks for Federated Multimodal Graph Foundation Learning
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 ...
-
TGHE: Template-based Graph Homomorphic Encryption for Privacy-Preserving GNN Inference in Edge-Cloud Systems
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.
-
Enhancing LLMs for Graph Tasks via Graph-aware LoRA Generation
GaRA generates task-specific LoRA weight updates conditioned on graph structures to enable better whole-graph encoding in LLMs for zero-shot graph learning.
-
CAMPA: Efficient and Aligned Multimodal Graph Learning via Decoupled Propagation and Aggregation
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.
-
Hierarchical Multi-Scale Graph Neural Networks: Scalable Heterophilous Learning with Oversmoothing and Oversquashing Mitigation
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.
-
No Need to Train Your RDB Foundation Model
Column-wise, parameter-free JUICE encodings let single-table ICL models solve multi-table RDB prediction tasks with no training or fine-tuning.
-
Revisiting Pre-Propagation GNNs: Robust Diffusion Operators and Hidden-State Re-Propagation
Robust diffusion operators and hidden-state re-propagation improve PPGNN accuracy to match message-passing GNNs on benchmarks.
-
Efficiently Learning Branching Networks for Multitask Algorithmic Reasoning
AutoBRANE learns tree-structured branching networks for multitask algorithmic reasoning via gradient-based task affinities and convex relaxation.
-
AdvSynGNN: Structure-Adaptive Graph Neural Nets via Adversarial Synthesis and Self-Corrective Propagation
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...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.