REVIEW 15 cited by
DeeperGCN: All You Need to Train Deeper GCNs
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
Signed reviews
read the original abstract
Graph Convolutional Networks (GCNs) have been drawing significant attention with the power of representation learning on graphs. Unlike Convolutional Neural Networks (CNNs), which are able to take advantage of stacking very deep layers, GCNs suffer from vanishing gradient, over-smoothing and over-fitting issues when going deeper. These challenges limit the representation power of GCNs on large-scale graphs. This paper proposes DeeperGCN that is capable of successfully and reliably training very deep GCNs. We define differentiable generalized aggregation functions to unify different message aggregation operations (e.g. mean, max). We also propose a novel normalization layer namely MsgNorm and a pre-activation version of residual connections for GCNs. Extensive experiments on Open Graph Benchmark (OGB) show DeeperGCN significantly boosts performance over the state-of-the-art on the large scale graph learning tasks of node property prediction and graph property prediction. Please visit https://www.deepgcns.org for more information.
Forward citations
Cited by 15 Pith papers
-
ORCAS: Obfuscation-Resilient Binary Code Similarity Analysis using Dominance Enhanced Semantic Graph
ORCAS shows that replacing control-flow edges with dominance, post-dominance, and data-flow relations makes binary code similarity search substantially more robust to BCF, FLA, and SUB obfuscation.
-
Towards Efficient Few-shot Graph Neural Architecture Search via Partitioning Gradient Contribution
GC splits a graph supernet into sub-supernets by grouping modules with similar gradient contributions, and UGAS searches combined MPNN and graph transformer architectures; the searched GNNs beat several baselines.
-
Can AI Agents Design and Implement Drug Discovery Pipelines?
The DO Challenge benchmark and Deep Thought multi-agent system show frontier LLM agents can roughly match non-expert humans on a synthetic virtual screening task, while remaining far behind expert-designed solutions.
-
DICE: Device-level Integrated Circuits Encoder with Graph Contrastive Pretraining
A self-supervised graph encoder for device-level circuits improves prediction of circuit similarity, delays, and op-amp performance across analog and digital designs.
-
Message-Passing GNNs Fail to Approximate Sparse Triangular Factorizations
Message-passing GNNs cannot approximate sparse triangular factorizations that require non-local dependencies, so building better learned preconditioners needs non-local or tailored architectures.
-
Graph Transformers for inverse physics: reconstructing flows around arbitrary 2D airfoils
A hybrid message-passing and linear-attention Graph Transformer reconstructs 2D airfoil flow fields from surface pressure alone, achieving high test accuracy on a new open dataset.
-
OMEGA: A Low-Latency GNN Serving System for Large Graphs
A distributed GNN serving system combines selective recomputation of precomputed embeddings with computation graph parallelism to achieve orders-of-magnitude lower serving latency with small accuracy loss.
-
Neighbor-Sampling Based Momentum Stochastic Methods for Training Graph Neural Networks
The paper creates Adam-style optimizers that combine neighbor sampling and control variates for graph neural networks, with optimal convergence rates and better node-classification performance than control-variate SGD.
-
Mitigating the Structural Bias in Graph Adversarial Defenses
De2GNN reduces degree bias in adversarial defenses by removing heterophilic links, adding homophilic links to tail nodes, and fusing a kNN feature view through node-wise attention, improving tail-node accuracy under M...
-
MolGraph-xLSTM: A graph-based dual-level xLSTM framework with multi-head mixture-of-experts for enhanced molecular representation and interpretability
MolGraph-xLSTM applies xLSTM to atom- and motif-level molecular graphs with a multi-head mixture-of-experts and reports benchmark gains on 10 property prediction datasets.
-
GraCo -- A Graph Composer for Integrated Circuits
GraCo uses reinforcement learning and graph consistency checks to jointly synthesize circuit topologies and transistor sizes, finding an inverter with about 5x fewer samples than random search and a faster NAND2 gate.
-
Enhancing Graph Representations with Neighborhood-Contextualized Message-Passing
SINC-GCN adds an aggregated neighborhood-context term to pair-wise messages, yielding a simple GNN that outperforms classical one-hop GNNs on several node and graph benchmarks.
-
PyG 2.0: Scalable Learning on Real World Graphs
PyG 2.0 is presented as a modular, scalable graph-learning framework with heterogeneous and temporal graph support, compilation-based speedups, and explainability.
-
Robust Anomaly Detection with Graph Neural Networks using Controllability
Using average controllability as edge weights or one-hot edge attributes yields small, inconsistent gains for graph anomaly detection across several GNN backbones.
-
Identifying Root Cause of bugs by Capturing Changed Code Lines with Relational Graph Neural Networks
A relational graph convolutional network with graph type conversion ranks deleted lines in bug-fixing commits and is reported to beat prior methods on Recall@1-3 and MFR, with no error bars or code release.
Discussion (0). Continue with ORCID to comment.