Graph Neural Networks (GNNs) are powerful to learn the representation of graph-structured data. Most of the GNNs use the message-passing scheme, where the embedding of a node is iteratively updated by aggregating the information of its neighbors. To achieve a better expressive capability of node influences, attention m…
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.
168,695 papers · 148 categories
Trend · papers per month
48 results for “attention aggregation”
This work explains the structural origins of attention sinks in LLMs.
problem Initial tokens disproportionately monopolize attention scores in LLMs.
method Traced to self-attention's value aggregation process and FFN layer activations.
result Attention sinks form due to variance discrepancy and dimension disparity.
AdaCAD improves semi-supervised classification by focusing on intra-class nodes.
problem Improving semi-supervised classification by addressing inter-class connections in graphs.
method AdaCAD uses a class-attentive diffusion process to adaptively aggregate nodes based on their class similarity.
result AdaCAD significantly outperforms state-of-the-art methods in semi-supervised classification.
MANA-Net improves market predictions by dynamically weighting news sentiments.
problem Aggregated Sentiment Homogenization in financial news data.
method Dynamic market-news attention mechanism to aggregate sentiments.
result MANA-Net outperforms recent market prediction methods by 1.1% Profit & Loss and 0.252 daily Sharpe ratio.
Non-local GNNs improve performance on disassortative graphs.
problem Efficiency and performance issues in local aggregation for disassortative graphs.
method Proposes a non-local aggregation framework with attention-guided sorting.
result Significantly outperforms previous methods on disassortative graphs.
Graph Attention Networks (GATs) are the state-of-the-art neural architecture for representation learning with graphs. GATs learn attention functions that assign weights to nodes so that different nodes have different influences in the feature aggregation steps. In practice, however, induced attention functions are pron…
Graph Neural Networks (GNNs) have proved to be an effective representation learning framework for graph-structured data, and have achieved state-of-the-art performance on many practical predictive tasks, such as node classification, link prediction and graph classification. Among the variants of GNNs, Graph Attention N…
AWARE improves graph prediction by aggregating walks with attention schemes.
problem Improving graph prediction accuracy using walk aggregation.
method Integrates attention schemes into walk-aggregating GNNs.
result AWARE outperforms existing methods in graph-level prediction tasks.
Although deep neural networks generally have fixed network structures, the concept of dynamic mechanism has drawn more and more attention in recent years. Attention mechanisms compute input-dependent dynamic attention weights for aggregating a sequence of hidden states. Dynamic network configuration in convolutional ne…
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.
A new method for deep multiple instance learning using self-attention.
problem Classifying bags of instances with dependencies.
method Introducing Self-Attention-based aggregation operation for bags of instances.
result SA-AbMILP outperforms other models in various datasets.
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.
We propose a dynamic neighborhood aggregation (DNA) procedure guided by (multi-head) attention for representation learning on graphs. In contrast to current graph neural networks which follow a simple neighborhood aggregation scheme, our DNA procedure allows for a selective and node-adaptive aggregation of neighboring …
Proposes a new optimization-based method for aggregating sets in neural networks.
problem Limited representational power of existing aggregation methods.
method Equilibrium Aggregation: an optimization-based approach.
result Equilibrium Aggregation outperforms existing methods in various tasks.
GEM detects malicious accounts using adaptive embeddings from heterogeneous graphs.
problem Detecting malicious accounts on a leading mobile payment platform.
method Adaptive learning of discriminative embeddings from heterogeneous account-device graphs with attention mechanism for node importance.
result GEM consistently outperforms competitive methods in detecting malicious accounts.
SCHA-VAE generates novel data from limited examples using hierarchical context aggregation.
problem Generating data from a novel distribution with limited examples.
method Hierarchical context aggregation with attention-based point to set-level aggregation.
result Hierarchical approach better captures intrinsic variability in small data.
A Trainable Optimal Transport Embedding for Feature Aggregation and its Relationship to Attentioncs.LG
Optimal transport embedding learns feature sets efficiently.
problem Learning on sets of features with long-range dependencies and few labeled data.
method Parametrized fixed-size embedding that aggregates features according to optimal transport plan.
result Achieves state-of-the-art results on protein fold recognition and chromatin profiles.
Aggregate network properties such as cluster cohesion and the number of bridge nodes can be used to glean insights about a network's community structure, spread of influence and the resilience of the network to faults. Efficiently computing network properties when the network is fully observed has received significant …
Enhanced GNN with expanded attention window and partially random embeddings.
problem Limited expressivity of traditional GNNs in distinguishing non-isomorphic graphs.
method Graph attention network with expanding attention window and partially random initial embeddings. Head dropout for regularization.
result Improved ability to differentiate between non-isomorphic graphs.
Analyzing a comprehensive news dataset, we document that joint news coverage triggers attention contagion, causing temporarily inflated valuations for affected stocks. Tracing SEC EDGAR visits from unique IPs, we provide direct evidence of attention spillovers between stocks. Stocks with greater joint news coverage exh…
Graph convolutional neural networks (GCNNs) have been attracting increasing research attention due to its great potential in inference over graph structures. However, insufficient effort has been devoted to the aggregation methods between different convolution graph layers. In this paper, we introduce a graph attribute…
The financial crisis showed the importance of measuring, allocating and regulating systemic risk. Recently, the systemic risk measures that can be decomposed into an aggregation function and a scalar measure of risk, received a lot of attention. In this framework, capital allocations are added after aggregation and can…
We introduce HTAD, a novel model for diagnosis prediction using Electronic Health Records (EHR) represented as Heterogeneous Information Networks. Recent studies on modeling EHR have shown success in automatically learning representations of the clinical records in order to avoid the need for manual feature selection. …
A new method for faster prediction in distributed Gaussian processes.
problem Inefficient aggregation of distributed Gaussian processes with correlations.
method Proposes a novel approach for aggregated prediction in distributed GPs that incorporates correlations among experts.
result Results in more stable predictions in less time compared to state-of-the-art methods.
GTEA: Inductive Representation Learning on Temporal Interaction Graphs via Temporal Edge Aggregationcs.LG
GTEA learns node representations in temporal interaction graphs.
problem Inductive representation learning on temporal interaction graphs.
method Integrates sequence model with time encoder and self-attention scheme for edge and node embeddings.
result GTEA learns comprehensive node representations capturing temporal and structural characteristics.
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…
Graph convolutional networks (GCNs) have recently become one of the most powerful tools for graph analytics tasks in numerous applications, ranging from social networks and natural language processing to bioinformatics and chemoinformatics, thanks to their ability to capture the complex relationships between concepts. …
New method aggregates bootstrapped DAGs for causal discovery.
problem Aggregation of bootstrapped DAGs ignores higher-order structures.
method Theoretical framework and new DAG aggregation algorithm.
result Proposed method outperforms state-of-the-art solutions.
Attention networks show promise for both vision and language tasks, by emphasizing relationships between constituent elements through weighting functions. Such elements could be regions in an image output by a region proposal network, or words in a sentence, represented by word embedding. Thus far the learning of atten…
Convergence of Message Passing Graph Neural Networks with Generic Aggregation On Large Random Graphsstat.ML
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.
GSANet improves semantic segmentation accuracy with selective and global attention.
problem Semantic segmentation accuracy improvement.
method Global and selective attention mechanism with ASPP and sparsemax.
result GSANet achieves state-of-the-art accuracy on ADE20k and Cityscapes datasets.
The celebrated Sequence to Sequence learning (Seq2Seq) technique and its numerous variants achieve excellent performance on many tasks. However, many machine learning tasks have inputs naturally represented as graphs; existing Seq2Seq models face a significant challenge in achieving accurate conversion from graph form …
AttViz offers online visualizations of neural language model attention mechanisms.
problem Limited interpretability of neural language models.
method Online toolkit for exploring self-attention mechanisms.
result Visualizations help understand model decision-making.
Attention operators have been widely applied in various fields, including computer vision, natural language processing, and network embedding learning. Attention operators on graph data enables learnable weights when aggregating information from neighboring nodes. However, graph attention operators (GAOs) consume exces…
The ability to adequately model risks is crucial for insurance companies. The method of "Copula-based hierarchical risk aggregation" by Arbenz et al. offers a flexible way in doing so and has attracted much attention recently. We briefly introduce the aggregation tree model as well as the sampling algorithm proposed by…
Policy-GNN optimizes GNN aggregation for diverse node iterations.
problem Optimizing GNN performance by varying aggregation iterations for different nodes.
method Policy-GNN uses a meta-policy framework with deep reinforcement learning to adaptively determine the number of aggregations for each node.
result Policy-GNN significantly outperforms state-of-the-art alternatives on real-world datasets.
Simpler GNNs with low-rank non-parametric aggregators perform well on graph benchmarks.
problem Over-engineering in GNN architectures for common semi-supervised node classification datasets.
method Replacing feature aggregation with a non-parametric learner to streamline GNN design.
result Non-parametric regression is effective for semi-supervised learning on sparse, directed networks.
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.
Transformer models waste resources on long-context tasks.
problem Redundant attention computations in Transformer models for long-context tasks.
method Reformulate sequence modeling as supervised learning, analyze attention sparsity, formulate attention optimization as linear coding problem, propose Dynamic Group Attention.
result DGA reduces computational costs while maintaining performance.
Multiple instance learning (MIL) is a variation of supervised learning where a single class label is assigned to a bag of instances. In this paper, we state the MIL problem as learning the Bernoulli distribution of the bag label where the bag label probability is fully parameterized by neural networks. Furthermore, we …
This paper explores methods for combining predictions in multilabel classification.
problem Lack of formal framework for aggregation in multilabel ensembles.
method Introduces two approaches: 'predict then combine' (PTC) and 'combine then predict' (CTP).
result Standard voting techniques are outperformed by tailored instantiations of CTP and PTC.
Attention-based GNNs can't prevent oversmoothing, leading to homogeneous node representations.
problem The issue of oversmoothing in attention-based GNNs.
method Viewed attention-based GNNs as nonlinear time-varying dynamical systems and used tools from the theory of products of inhomogeneous matrices and the joint spectral radius.
result Graph attention mechanism cannot prevent oversmoothing and loses expressive power exponentially.
Social recommendation has emerged to leverage social connections among users for predicting users' unknown preferences, which could alleviate the data sparsity issue in collaborative filtering based recommendation. Early approaches relied on utilizing each user's first-order social neighbors' interests for better user …
In general, a self-attention mechanism has been applied for speaker embedding encoding. Previous studies focused on training the self-attention in a high-level layer, such as the last pooling layer. However, the effect of low-level features was reduced in the speaker embedding encoding. Therefore, we propose masked cro…
In this work, we explore the impact of visual modality in addition to speech and text for improving the accuracy of the emotion detection system. The traditional approaches tackle this task by fusing the knowledge from the various modalities independently for performing emotion classification. In contrast to these appr…
Proposes a novel node embedding framework for graphs using Fisher Information.
problem Lack of theoretical understanding of attention-based GNNs.
method Uses hierarchical kernels and Fisher Information to learn node embeddings.
result Proposed method outperforms existing GNNs on node classification benchmarks.
FMA-ETA predicts travel time using FFN with attention.
problem Estimating travel time from spatial-temporal data.
method FFN with Multi-factor self-attention mechanism.
result FMA-ETA outperforms state-of-the-art methods in prediction accuracy with faster inference.
Crowdsourcing is a relatively economic and efficient solution to collect annotations from the crowd through online platforms. Answers collected from workers with different expertise may be noisy and unreliable, and the quality of annotated data needs to be further maintained. Various solutions have been attempted to ob…