New bounds for quantile aggregation unify and clarify existing methods.
problem Analytical bounds for quantile aggregation with dependence uncertainty.
method Using inf-convolution of quantile-based risk measures, establish new analytical bounds called convolution bounds.
result Convolution bounds are the best available and provide sharp results in many cases.
GmCN adapts GCN feature aggregation to improve graph learning.
problem Fixed neighborhood graph aggregation in GCNs is biased and can be affected by graph structure noises.
method GmCN allows nodes to adaptively select optimal neighbors for feature aggregation.
result GmCN improves graph learning effectiveness through adaptive neighbor selection.
GAAN uses progressive margin folding for graph feature aggregation.
problem Insufficient aggregation methods between GCNN layers.
method Graph attribute aggregation network with progressive margin folding.
result GAAN outperforms existing GCNN models on molecule datasets.
GCNs improve regression tasks by aggregating neighbor signals.
problem GCNs' statistical properties in regression tasks are poorly understood.
method Examined two GCN convolutions and their impact on learning error.
result GCNs have a bias-variance trade-off that depends on neighborhood size and topology.
Improves GCN by sampling neighbors and features for better node representation.
problem GCN's aggregation process treats all neighbors and features equally, leading to suboptimal node representations.
method Introduces a new convolution operation on feature maps constructed from a fixed node bandwidth, then passes to a standard GCN.
result Outperforms competing methods in semi-supervised node classification tasks.
Enhances DenseNets with multi-scale convolutions and stochastic feature reuse.
problem Overfitting in DenseNets with dense feature reuse.
method Multi-scale Convolution Aggregation module and Stochastic Feature Reuse.
result Significant improvement in model accuracy with fewer parameters.
Two architectures that generalize convolutional neural networks (CNNs) for the processing of signals supported on graphs are introduced. We start with the selection graph neural network (GNN), which replaces linear time invariant filters with linear shift invariant graph filters to generate convolutional features and r…
Geom-GCN improves graph neural networks by preserving structural information and capturing long-range dependencies.
problem Weaknesses in MPNNs' aggregators: loss of structural information and lack of long-range dependencies.
method Proposes a geometric aggregation scheme with three modules: node embedding, structural neighborhood, and bi-level aggregation.
result Achieved state-of-the-art performance on various graph datasets.
Global Planar Convolution boosts brain tumor segmentation by enhancing context perception.
problem Improving context perception in brain tumor segmentation networks.
method Introduced Global Planar Convolution module to enhance context aggregation in brain tumor segmentation.
result Global Planar Convolution eliminates the need for multiple representation levels in segmentation networks.
HKConv learns hyperbolic features by aggregating kernel points.
problem Challenges in learning good hyperbolic representations using Euclidean operations.
method Proposes HKConv, a trainable hyperbolic convolution that correlates local features with kernel points and aggregates them.
result HKConv learns expressive local features according to hyperbolic geometry and enjoys equivariance to permutation and invariance to parallel transport.
Paper provides new bounds for risk aggregation and sharing.
problem Quantitative risk management and robust risk aggregation with dependence uncertainty.
method Established new inequality for RVaR, derived extended convolution bounds, and analyzed risk sharing for averaged quantiles.
result Extended convolution bounds for robust risk aggregation and risk sharing, providing sharpness conditions and explicit expressions.
Study on convergence of graph neural networks on random graphs.
problem Convergence of message passing graph neural networks on large random graphs.
method Extended convergence results to a broad class of aggregation functions using McDiarmid inequality.
result Non-asymptotic bounds for convergence quantified with high probability.
ie-HGCN addresses HIN challenges by efficiently learning node representations.
problem Lack of flexibility in exploring meta-paths and high computational complexity in HIN GCN methods.
method Hierarchical aggregation architecture that automatically extracts useful meta-paths and reduces computational cost.
result ie-HGCN outperforms state-of-the-art methods on real network datasets.
H-GCN enhances GCNs by pooling nodes to hyper-nodes for better global information.
problem Limited global information in shallow GCNs for semi-supervised node classification.
method Hierarchical graph pooling and refinement of coarsened graphs.
result H-GCN outperforms state-of-the-art methods on various graph datasets.
DrGCN improves GCNs by addressing dimensional imbalance.
problem Dimensional imbalance in node representations of graphs.
method Dimensional reweighting method combined with GCN.
result DrGCN improves GCNs' stability and outperforms existing models.
SWAG uses graph convolutions to recommend products.
problem Product recommendation using graph-structured data.
method Graph Convolutional Network (GCN) with weighted random walks and aggregations.
result Graph-based approach improves product recommendations.
A new framework uses deep RL to aggregate expert advice for better portfolio management.
problem Improving portfolio management through expert advice and deep reinforcement learning.
method Convolutional networks for signal aggregation and historical price data, Proximal Policy Optimization algorithm.
result Our framework can achieve 90% of the best expert's profit on average.
DeeperGCN tackles deep GCNs by overcoming vanishing gradient and over-smoothing issues.
problem Vanishing gradient, over-smoothing, and over-fitting issues in deep GCNs.
method DeeperGCN uses differentiable generalized aggregation functions and a novel normalization layer (MsgNorm) to train deep GCNs.
result DeeperGCN significantly boosts performance on large-scale graph learning tasks.
Finding the most effective way to aggregate multi-subject fMRI data is a long-standing and challenging problem. It is of increasing interest in contemporary fMRI studies of human cognition due to the scarcity of data per subject and the variability of brain anatomy and functional response across subjects. Recent work o…
Augments GNNs with diversification to preserve node identity.
problem Current GNNs filter node information, potentially losing node identity.
method Integrates diversification operators with aggregation to enrich node representations.
result Significant performance boost on 9 node classification tasks.
DAGCN improves graph classification by learning neighbor importance and pooling.
problem Loss of early-stage information and loss of node characteristics in GCNs.
method Dual attention graph convolution and self-attention pooling.
result DAGCN outperforms state-of-the-art methods in graph classification.
HTGCN improves community detection in dynamic, heterogeneous graphs.
problem Challenges in detecting communities in graphs with varying features and temporal dynamics.
method Designs HTGCN combining heterogeneous GCN and residual compressed aggregation for dynamic feature representation.
result HTGCN outperforms existing methods on DBLP and IMDB datasets.
The paper introduces a new loss function to prevent overfitting in semi-supervised graph networks.
problem Overfitting in semi-supervised graph networks trained with cross-entropy loss.
method Proposes an unsupervised manifold smoothness loss to regularize the graph convolutional networks.
result Adding the proposed loss consistently improves performance of graph networks.
Improved disentanglement in VAEs using aggregated feature maps.
problem Improving disentanglement in Variational Autoencoders (VAEs).
method Regionally aggregated feature maps extracted from pre-trained CNNs on ImageNet.
result 2nd place in NeurIPS 2019 disentanglement challenge.
A new linear GCN model improves recommendation performance for large graphs.
problem Training difficulties and over-smoothing in GCN-based CF models.
method Proposes a linear residual graph convolutional network (LRGCCF) to address training difficulties and over-smoothing issues.
result The proposed model yields better efficiency and effectiveness on real datasets.
SStaGCN improves GCN by stacking and aggregation for better node feature extraction.
problem Mitigating over-smoothing in GCN for heterogeneous graph data.
method SStaGCN combines stacking and aggregation to improve GCN performance.
result SStaGCN effectively mitigates over-smoothing and enhances node feature extraction.
A convolutional sequence to sequence non-intrusive load monitoring model is proposed in this paper. Gated linear unit convolutional layers are used to extract information from the sequences of aggregate electricity consumption. Residual blocks are also introduced to refine the output of the neural network. The partiall…
We present our ongoing work on understanding the limitations of graph convolutional networks (GCNs) as well as our work on generalizations of graph convolutions for representing more complex node attribute dependencies. Based on an analysis of GCNs with the help of the corresponding computation graphs, we propose a gen…
We develop a secure aggregation protocol for federated learning that reduces communication and computation costs.
problem Expensive communication and privacy concerns in federated learning.
method Adapting compression-based federated techniques to additive secret sharing.
result Our protocol achieves high accuracy with low communication costs and is more efficient than prior work.
Proposes a 2-WL-based graph convolution for improved graph classification.
problem Limitations of current GNN architectures in discriminative power.
method Introduces a novel 2-dimensional Weisfeiler-Lehman graph convolution.
result 2-WL-GNN architecture is more discriminative than existing GNN approaches.
Enhances graph neural networks by considering feature similarities in node aggregation.
problem Ignoring node feature similarities in traditional graph aggregation schemes.
method Interprets node aggregation as kernel weighting, proposing a framework that considers feature similarities.
result Proposed framework outperforms traditional GCNs in real-world applications.
Improved disentanglement through learned feature aggregation.
problem Disentangling latent factors in images.
method Variational autoencoder trained on regionally aggregated feature maps from ImageNet.
result 2nd place in NeurIPS 2019 disentanglement challenge.
RDL-Net improves speech enhancement with fewer parameters and better performance.
problem Improving speech enhancement with fewer parameters and better performance.
method Proposes RDL-Net, a CNN combining residual and dense aggregations without over-allocating parameters.
result RDL-Net achieves higher speech enhancement performance with fewer parameters and lower computational requirements.
RGCF improves collaborative filtering by refining graph convolution embeddings.
problem GCN-based recommendation models introduce noise and redundancy, limiting high-order connectivity capture.
method Developed RGCF, a new GCN-based Collaborative Filtering model with redesigned embeddings.
result RGCF significantly outperforms state-of-the-art models on public datasets.
RR-GCN uses random transformations instead of learned weights for node embeddings.
problem Learning node embeddings in KGs.
method Random Relational Graph Convolutional Network (RR-GCN) with untrained parameters.
result RR-GCN can compete with fully trained R-GCNs in node classification and link prediction.
GraphAIR improves graph representation learning by capturing non-linear interactions.
problem Challenges in capturing non-linear interactions in graph data.
method Integrates neighborhood aggregation and interaction modeling.
result Demonstrates improved performance on node classification and link prediction tasks.
ConfGCN estimates labels and confidences in graph-based semi-supervised learning.
problem Predicting node properties in graphs with limited labeled data.
method ConfGCN uses graph convolutional networks to estimate labels and confidences jointly, improving upon anisotropic neighborhood aggregation.
result ConfGCN outperforms state-of-the-art baselines on standard benchmarks.
Single-layer GCN model improves recommendation performance with less complexity.
problem Severe computational burden and excessive model parameters in existing GCN models.
method Proposes a single-layer GCN architecture with a simplified aggregation step using DA similarity.
result Significantly outperforms existing GCN models and achieves up to a few orders of magnitude speedup.
GradiVeQ reduces CNN training time by 50% with 5X faster gradient aggregation.
problem Significant communication costs in gradient aggregation for distributed CNN training.
method GradiVeQ uses PCA to vector quantize gradients for direct RAR aggregation.
result GradiVeQ reduces wall-clock gradient aggregation time by more than 5X.
Efficient neural network for audio source separation.
problem End-to-end general purpose audio source separation.
method SuDoRMRF structure with simple one-dimensional convolutions for feature aggregation.
result SuDoRMRF achieves high quality audio source separation with minimal computational resources.
Develops a distributed strategy for Pareto optimization of aggregate costs with smoothed regularizers.
problem Optimizing aggregate costs with non-smooth regularizers in a network of agents.
method Distributed strategy using infimal convolution to smooth regularizers, seeking Pareto optimal solution via diffusion.
result Pareto solution of smoothed problem can be made arbitrarily close to original non-smooth problem.
Monotone aggregation of dependent random vectors has an absolutely continuous distribution under certain conditions.
problem Monotone aggregation of dependent random vectors
method Coordinatewise monotonicity and uniform lower-increment conditions
result One-dimensional push-forwards of dependent random vectors have an absolutely continuous distribution
Graph convolutional network (GCN) is generalization of convolutional neural network (CNN) to work with arbitrarily structured graphs. A binary adjacency matrix is commonly used in training a GCN. Recently, the attention mechanism allows the network to learn a dynamic and adaptive aggregation of the neighborhood. We pro…
Improved algorithm speeds up generation of universal adversarial perturbations.
problem Slow generation of universal adversarial perturbations.
method Optimized algorithm based on orientation of perturbation vectors.
result Significantly faster generation of universal perturbations with higher fooling rates.
DSGC improves graph representation learning by modeling object links and attribute relations.
problem Limited modeling capability of existing GCN variants on noisy and sparse real-world networks.
method Dimensionwise separable 2-D graph convolution (DSGC) that filters node features.
result DSGC achieves significant performance gain over state-of-the-art methods for node classification and clustering.
Indirect attacks can fool graph classifiers even with poisoned neighbors.
problem How to evaluate and defend graph convolutional neural networks against indirect adversarial attacks.
method Proposed a method to generate adversarial perturbations on a single node far from the target.
result 99% attack success rate within two-hops from the target in two datasets.
Bayesian deep learning counts crowds robustly despite occlusions and scale variations.
problem Accurately counting individuals in crowded scenes with occlusions and varying sizes.
method Proposes a Bayesian multi-scale neural network with a ResNet feature extractor, dilated convolutions, and a Perspective-aware Aggregation Module.
result Achieves superior performance on crowd counting benchmarks with uncertainty estimates.
S4 model improves long sequence modeling efficiency.
problem Handling long-range dependencies efficiently in convolutional models.
method S4 model uses global convolution with decaying kernel weights.
result SGConv model achieves similar performance to S4 with improved efficiency.