Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,236 papers · 148 categories

Trend · papers per month

255075100 · Jun 202619922001200920182026
48 results for Neighborhood aggregation

Revises GNN neighborhood aggregation for more accurate node classification.

problem Flaws in benchmark GNN models for node classification.
method Statistical signal processing approach to neighborhood aggregation.
result Novel insights for designing more efficient GNN models.

DNA improves graph neural networks by selectively aggregating node embeddings.

problem Static neighborhood aggregation limits graph neural networks' performance.
method Dynamic neighborhood aggregation guided by attention and controlled channel connections.
result DNA outperforms current methods in transductive node classification.

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.

NEAR improves graph classification by aggregating edge information.

problem Loss of local structure and relationships in 1-hop neighborhood GNNs.
method Proposes NEAR, a framework that aggregates edge information between nodes in the neighborhood.
result NEAR improves graph classification tasks over existing 1-hop based GNN algorithms.

A new GNN model SPIN achieves state-of-the-art performance on diverse real-world datasets.

problem Graph classification efficiency and accuracy.
method Parallel neighborhood aggregations (PA-GNNs) and SPIN model.
result SPIN model achieves state-of-the-art performance on diverse real-world datasets.

Paper extends topic models using neighborhood aggregation for better performance.

problem Extending topic models with pre-trained word embeddings and nonlinear output functions.
method Network view of topic models, neighborhood aggregation algorithm.
result Approach outperforms state-of-the-art supervised Latent Dirichlet Allocation.

Develops GNNs for incomplete graphs, improving learning from missing node attributes.

problem Learning from incomplete graphs with missing node attributes.
method Introduces PaGNNs with novel partial aggregation functions for incomplete graph data.
result Demonstrates effectiveness and efficiency of PaGNNs on various datasets.

CoarsenRank improves robustness in rank aggregation despite model misspecification.

problem Rank aggregation under model misspecification in real-world scenarios.
method CoarsenRank designs a neighborhood of ideal preferences to handle agnostic noise-corrupted data.
result CoarsenRank achieves robustness against model misspecification within a defined neighborhood.

JK networks adapt to varying neighborhood sizes for better graph representation learning.

problem Fixed neighborhood aggregation limits model performance on graphs with diverse structures.
method Jumping Knowledge (JK) networks that use different neighborhood sizes for each node.
result JK networks achieve state-of-the-art performance on various graph 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.

The paper introduces a method to control false splits in tree-based data aggregation.

problem Identifying the correct subgroups to treat as a single entity in tree-based data.
method Introduces the 'false split rate' and proposes a multiple hypothesis testing algorithm for tree-based aggregation.
result The proposed algorithm controls the false split rate, demonstrating its effectiveness on stock volatility and taxi fare data.

Graph Denoising Policy Network learns robust representations from noisy graphs.

problem Noise sensitivity in graph representation learning.
method Reinforcement learning to select signal neighborhoods and aggregate features.
result Significantly outperforms state-of-the-art methods on node classification tasks.

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.

GraLSP improves graph neural networks by incorporating local structural patterns.

problem GNNs struggle with identifying common structural patterns in graphs.
method GraLSP uses random anonymous walks to capture local graph structures and incorporates these into feature aggregation mechanisms.
result GraLSP outperforms other models in various prediction tasks on multiple datasets.

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.

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.

New aggregation method improves GNN robustness to structural perturbations.

problem Graph Neural Networks (GNNs) are vulnerable to adversarial attacks that manipulate graph structure.
method Proposes a robust aggregation function with a breakdown point of 0.5, inspired by robust statistics.
result Improves GNN robustness by a factor of 3 on Cora ML and 5.5 on Citeseer, and 8 for low-degree nodes.

Enhances generative models with latent features and neighborhood memories.

problem Current generative models only use one of two components: learned features or instance recall.
method Proposes methods to integrate neighborhood information into a flow model's latent space.
result Empirically shows significant improvement over baselines on image datasets.

A new data-driven sampling method improves GraphSAGE's accuracy in node classification.

problem High variance in neighborhood sampling leads to sub-optimum accuracy in GraphSAGE.
method A data-driven node sampling approach using a non-linear regressor trained with reinforcement learning.
result Enhanced GraphSAGE accuracy in inductive node classification benchmarks.

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.

LATTE tackles heterogeneous network embedding challenges with layer-stacked attention.

problem Aggregating higher-order indirect relations in heterogeneous networks.
method Layer-stacked ATTention Embedding (LATTE) that decomposes meta relations at each layer.
result LATTE achieves state-of-the-art performance on benchmark datasets.

F-GCN improves graph convolutional networks for semi-supervised node classification.

problem Improving representation capacity of graph convolutional networks for multi-hop neighborhood information.
method Proposes a mathematically motivated, yet simple extension to existing GCNs.
result F-GCN outperforms state-of-the-art models on six out of eight datasets.

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.

Maximizes mutual information to improve graph neural networks performance.

problem Loss of information between nodes in GNNs aggregation and iteration schemes.
method Explores mutual information maximization in the aggregation and iteration scheme of GNNs.
result Improves state-of-the-art performance on graph tasks.

Proposes CGA model for logical queries over KGs.

problem Handling logical queries over incomplete KGs with unequal query path contributions.
method Multi-head graph attention with initial neighborhood aggregation for center node prediction.
result CGA model outperforms baselines on DB18, WikiGeo19, and Bio datasets.

We analyze and generalize graph convolutions for better node attribute representation.

problem Limitations of existing graph convolutional networks (GCNs).
method Proposed a generalization of GCNs with structural properties of local neighborhood graphs and non-weighted aggregation operations.
result The proposed approach is strictly more expressive with a modest increase in parameters and computations.

A new ensemble method improves kNN performance by extending the neighborhood rule.

problem Traditional kNN's limitations when test points are outside the spherical region and ensemble's high errors.
method Determines neighbors in k steps, using bootstrap samples and optimal models selection.
result The proposed ensemble method outperforms state-of-the-art methods on 17 benchmark datasets.

New approach to deeper graph neural networks to avoid performance degradation.

problem Performance degradation of graph neural networks when going deeper.
method Decoupling representation transformation and propagation in graph convolution operations.
result Deeper graph neural networks can be used to learn graph node representations from larger receptive fields.

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.

In this short paper we define the wealth process in a spin model for market microstructure, for individual agents and in aggregate. The agents in our model try to balance their desire to belong to the local majority (herding behavior), defined over random network neighborhoods, and the occasional advantage of belonging…

2005-02-07abs ↗pdf ↗

Individual choices are either based on personal experience or on information provided by peers. The latter case, causes individuals to conform to the majority in their neighborhood. Such herding behavior may be very efficient in aggregating disperse private information, thereby revealing the optimal choice. However if …

2005-06-17abs ↗pdf ↗

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.

SGATs learn sparse attention coefficients to improve graph learning tasks on large, noisy graphs.

problem Overfitting and noisy edges in GNNs on large, noisy graphs.
method Sparse Graph Attention Networks (SGATs) learn sparse attention coefficients under L0L_0-norm regularization.
result SGATs can remove 50%-80% edges from large graphs while maintaining similar classification accuracies.

A method to robustly federate learning with non-i.i.d. data and Byzantine workers.

problem Byzantine workers sending malicious messages in federated learning with non-i.i.d. data.
method Resampling strategy to reduce inner and outer variation, stochastic average gradient, robust geometric median aggregation.
result The method reaches a neighborhood of the optimal solution at a linear convergence rate and learning error depends on the number of Byzantine workers.

GNNs are powerful but limited in their ability to distinguish certain graph structures.

problem Limited understanding of GNNs' representational properties and limitations.
method Theoretical framework and analysis of GNN expressive power, development of a provably most expressive GNN architecture.
result GNNs cannot learn to distinguish certain simple graph structures, but a new architecture can.