Spectral Networks and Locally Connected Networks on Graphs
read the original abstract
Convolutional Neural Networks are extremely efficient architectures in image and audio recognition tasks, thanks to their ability to exploit the local translational invariance of signal classes over their domain. In this paper we consider possible generalizations of CNNs to signals defined on more general domains without the action of a translation group. In particular, we propose two constructions, one based upon a hierarchical clustering of the domain, and another based on the spectrum of the graph Laplacian. We show through experiments that for low-dimensional graphs it is possible to learn convolutional layers with a number of parameters independent of the input size, resulting in efficient deep architectures.
This paper has not been read by Pith yet.
Forward citations
Cited by 20 Pith papers
-
Learning Laplacian Eigenspace with Mass-Aware Neural Operators on Point Clouds
NEO is a mass-aware neural operator that learns the invariant low-frequency eigenspace of the LBO on point clouds for fast spectral geometry.
-
FlexVector: A SpMM Vector Processor with Flexible VRF for GCNs on Varying-Sparsity Graphs
FlexVector achieves 3.78x speedup and 40.5% lower energy for GCN inference on five real-world datasets by using flexible VRFs and graph preprocessing to match varying-sparsity graphs.
-
Rodrigues Network for Learning Robot Actions
Proposes Rodrigues Network using a learnable Neural Rodrigues Operator to add kinematic inductive biases for improved robot action learning and prediction.
-
A Benchmark Dataset for Graph Regression with Homogeneous and Multi-Relational Variants
RelSC is a new graph regression benchmark from program graphs with execution time labels, released in homogeneous (RelSC-H) and multi-relational (RelSC-M) variants to study representation effects.
-
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.
-
Ada-Diffuser: Latent-Aware Adaptive Diffusion for Decision-Making
Ada-Diffuser is a causal diffusion model that jointly learns observed interaction structure and underlying latent dynamics from minimal observations for adaptive planning and policy learning.
-
ASPIRE: Make Spectral Graph Collaborative Filtering Great Again via Adaptive Filter Learning
ASPIRE learns adaptive graph filters via bi-level optimization to overcome low-frequency explosion bias in spectral collaborative filtering, achieving strong performance and stability.
-
Uniform Inductive Spatio-Temporal Kriging
UniSTOK improves inductive spatio-temporal kriging under incomplete observations by reliability-guided signal regulation and residual bias calibration.
-
When Structure Doesn't Help: LLMs Do Not Read Text-Attributed Graphs as Effectively as We Expected
LLMs achieve strong results on text-attributed graphs using only node textual descriptions, while most methods for encoding graph structure deliver marginal or negative gains.
-
Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks
DGL is a graph-centric library that optimizes GNNs via generalized sparse tensor operations, transparent graph-based optimizations, and framework-neutral design, claiming superior speed and memory use over other GNN f...
-
A Zero-shot Generalized Graph Anomaly Detection Framework via Node Reconstruction
AlignGAD is a zero-shot generalized graph anomaly detection framework using a Global Unification Module, Clustering Module, and Node Discrepancy Scoring Module.
-
A Graph Foundation Model with Spectral Parsing and Prototype-Guided Spatial Propagation
SPG is a graph foundation model using spectral decomposition via Chebyshev filters and Gromov-Wasserstein prototypes for improved cross-graph transferability.
-
Graph Transductive Sharpening: Leveraging Unlabeled Predictions in Node Classification
Transductive Sharpening adds an entropy-minimization term on unlabeled-node predictions to the training objective for graph node classification.
-
Make Your LVLM KV Cache More Lightweight
LightKV compresses vision-token KV cache in LVLMs to 55% size via prompt-guided cross-modality aggregation, halving cache memory, cutting compute 40%, and maintaining performance on benchmarks.
-
Efficient and Scalable Granular-ball Graph Coarsening Method for Large-scale Graph Node Classification
A multi-granularity granular-ball coarsening algorithm reduces large graphs in linear time for faster GCN training on node classification, with experiments claiming superior performance over prior methods.
-
RankGraph-2: Lifecycle Co-Design for Billion-Node Graph Learning in Recommendation
RankGraph-2 jointly optimizes graph subsampling, pre-computed neighborhoods, and a co-learned cluster index for billion-node recommendation retrieval, reporting 3.8x recall gains and up to +0.96% CTR.
-
RankGraph-2: Lifecycle Co-Design for Billion-Node Graph Learning in Recommendation
RankGraph-2 jointly optimizes graph construction, training, and serving for billion-node recommendation retrieval, reporting 3.8x recall gains and CTR/CVR improvements via subsampling, pre-computed neighborhoods, and ...
-
Topology-Aware Gaussian Graph Repair for Robust Graph Neural Networks
TAGR repairs graphs with sparse Gaussian feature-neighborhood edges plus topology-aware residual correction to boost GNN robustness on noisy or incomplete citation networks.
-
PH-GCN: Person Re-identification with Part-based Hierarchical Graph Convolutional Network
PH-GCN constructs a hierarchical graph of person parts and performs local/global feature learning via message passing in an end-to-end network for person re-identification.
-
A review on deep learning techniques for 3D sensed data classification
A survey of deep learning architectures for 3D sensed data classification covering RGB-D, multi-view, volumetric and end-to-end methods along with datasets and future directions.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.