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.

168,932 papers · 148 categories

Trend · papers per month

25.0%50.0%75.0%100.0% · Sep 199219922001200920172026
48 results for structure fusion

SF-GCN improves semi-supervised classification by fusing multi-view data structures.

problem Semi-supervised classification challenges due to multi-view data diversity and complexity.
method Structure fusion based on graph convolutional networks (SF-GCN) that balances specificity and commonality.
result SF-GCN outperforms state-of-the-art methods on citation networks datasets.

Fusion framework improves time series classification across different datasets.

problem Kernel-based methods like Rocket perform inconsistently across datasets.
method Fusion-3 framework that adaptively fuses three representations (Rocket, SAX, SFA) based on dataset properties.
result Fusion-3 framework yields small but consistent average improvements over Rocket on 113 UCR datasets.

The importance of the fusion relation of loops was recognized in the context of spin structures on the loop space by Stolz and Teichner and further developed by Waldorf. On a spin manifold M the equivalence classes of `fusive' spin structures on the loop space LM, incorporating the fusion property, strong regularity an…

2013-09-01abs ↗pdf ↗

Study improves robustness of deep fusion models against single source noise.

problem Ensuring robustness of deep fusion models against noise added to a single input source.
method Proposed two approaches: a carefully designed loss function and a convolutional fusion layer.
result Deep fusion models become robust against noise applied to a single source, preserving performance on clean data.

String-net models explore non-spherical fusion categories, revealing new spin structures and representations.

problem Investigating string-net models in non-spherical fusion categories.
method String-net models associate vector spaces to surfaces in terms of graphs decorated by objects and morphisms of a pivotal fusion category.
result String-net spaces count r-spin structures and carry representations of the mapping class group.

Paper analyzes deep learning models for credit rating prediction using text and numerical data.

problem Improving credit rating prediction using multi-modal deep learning.
method Testing different deep learning models and fusion strategies for structured and unstructured datasets.
result CNN-based multi-modal model with two fusion strategies outperformed other models.

Paper introduces topological eigenvalue theorems for tensor analysis in multi-modal data.

problem Lack of deep understanding of tensor structures in multi-modal data fusion.
method Introduces topological perspective to tensor eigenvalue analysis, linking eigenvalues to topological features.
result Establishes new theorems that enhance understanding of tensor structures in data fusion.

Proposes SROF for row-wise fusion in federated learning for multivariate responses.

problem Heterogeneous client models with shared variable-level structure.
method Sparse Row-wise Fusion (SROF) regularizer and RowFed algorithm.
result Empirically shows consistent error reduction and stronger variable-level cluster recovery.

Adversarial approach enhances sensor fusion for robust target detection.

problem Improving target detection and classification using multi-modal sensor fusion.
method Generative network learns latent space from various sensor modalities, then detects damaged sensors and safeguards performance.
result Automatic robustness against noisy/damaged sensors achieved.

We construct a state-sum type invariant of smooth closed oriented 44-manifolds out of a GG-crossed braided spherical fusion category (GG-BSFC) for GG a finite group. The construction can be extended to obtain a (3+1)(3+1)-dimensional topological quantum field theory (TQFT). The invariant of 44-manifolds generalizes s…

2016-10-24abs ↗pdf ↗

New method fuses audio and magnetic data to identify underlying subspaces.

problem Identifying complex trends in multi-modality data.
method Robust Group Subspace Recovery (RoGSuRe) algorithm based on group sparsity and bi-sparsity pursuit.
result Competitive performance in clustering and classification of multi-modal data.

Proposes C2AF network for multi-view time series classification.

problem Improving multi-view time series classification performance.
method Two-stream structured encoder, graph-based correlation matrix, channel-aware fusion mechanism.
result Extensive experimental results show superior performance over state-of-the-art methods.

Inspired by brain's modality fusion, this paper detects active speakers from audio and video.

problem Detecting active speakers in noisy environments.
method Inspired by brain's superior colliculus, combines audio and visual data through specialized neural networks and a novel fusion layer.
result Achieved results greatly surpassing initial expectations, confirming the effectiveness of the proposed method.

A new method for feature fusion in U-Net decoders using difference-based gating.

problem Precise fusion of high-level semantics and low-level details in U-Net decoder reconstruction.
method Proposes two difference-based gating approaches: Feature-difference gating (FDG) and Entropy-difference gating (EDG).
result Both FDG and EDG methods outperform existing attention-based fusion methods, with EDG showing superior performance.

Proposes GRAB-MDM for robust multiview data fusion.

problem Limited theoretical guarantees for multiview fusion methods in noisy high-dimensional data.
method Generalized Robust Adaptive-Bandwidth Multiview Diffusion Maps (GRAB-MDM) with adaptive bandwidth selection.
result Adaptive bandwidths lead to robust recovery of shared intrinsic structure in noisy multiview data.

The paper constructs braiding structures for a specific subfactor.

problem The challenge is to understand the braiding structures of a Jones-Wassermann subfactor.
method The approach involves constructing braiding structures on the multi-interval Jones-Wassermann subfactor planar algebra.
result The braiding structures induce a projective unitary representation of the balanced superelliptic mapping class group.

Proposes a fusion method for many treatment groups in ITRs.

problem Challenges in handling many treatment groups with data sparsity and covariate imbalance.
method Calibration-weighted treatment fusion procedure that balances covariates and fuses similar treatments.
result Ensures robust treatment group recovery and policy value compared to existing methods.

Meta Fusion integrates various multimodal data fusion strategies into a unified framework.

problem Improving predictive power of machine learning methods across diverse applications.
method Meta Fusion constructs a cohort of models based on latent representations across modalities, sharing soft information to boost performance.
result Meta Fusion consistently outperforms conventional fusion strategies in simulation and real-world applications.

PG-EVIKAL refines molecular property predictions using neighbor fusion and evidential neural networks.

problem Improving molecular property predictions using test-time neighbor fusion.
method Adapting evidential neural networks to refine predictions by re-ranking structurally similar neighbors.
result PG-EVIKAL reduces RMSE on 14 out of 16 molecular datasets, improving calibration and sequential refinement.

Improved accuracy in dynamic response variation analysis using multi-fidelity data fusion.

problem Inefficient characterization of dynamic response variation due to limited high-fidelity data.
method Composite Neural Network fusion approach for multi-level, heterogeneous datasets.
result Improved accuracy in frequency response variation characterization.

A new memory-based fusion layer improves multi-modal deep learning performance.

problem Improving performance of multi-modal deep learning by addressing long-term dependencies.
method Introducing a Memory based Attentive Fusion (MBAF) layer that incorporates both current and long-term dependencies.
result The MBAF layer enhances fusion and improves performance across different modalities and networks.

Study improves stock movement prediction using multimodal data.

problem Inaccurate stock movement prediction due to incomplete multimodal data integration.
method Introduces MSGCA framework for robust multimodal fusion.
result MSGCA framework outperforms existing methods by 21.7% on multimodal datasets.

We analyze a functor from cyclic operads to chain complexes first considered by Getzler and Kapranov and also Markl. This functor is a generalization of the graph homology considered by Kontsevich, which was defined for the three operads Comm, Assoc, and Lie. More specifically we show that these chain complexes have a …

2002-08-12abs ↗pdf ↗

This paper improves model fusion by training-time neuron alignment, reducing barriers in multi-model fusion.

problem Diverse neuron permutations across different settings hinder model fusion performances.
method Training-time neuron alignment using fixed neuron anchors to reduce training-time permutations.
result Training-time neuron alignment improves fusion of pretrained models and federated learning performances.

We classify all fusion categories for a given set of fusion rules with three simple object types. If a conjecture of Ostrik is true, our classification completes the classification of fusion categories with three simple object types. To facilitate the discussion we describe a convenient, concrete and useful variation o…

2007-04-02abs ↗pdf ↗

Novel fusion network combines polarization and radiomics features for liver cancer classification.

problem Challenges in histopathological diagnosis of HCC and ICC.
method Two-tier fusion approach: feature-level and classification-level.
result Significantly enhances classification accuracy, even at reduced resolutions.

Study fusion methods for financial image views to improve robustness against attacks.

problem Improving robustness of financial image views for next-day direction prediction.
method Same-source multi-view learning with early fusion and late fusion, using OHLCV and technical-indicator views, and evaluating pixel-space L-infinity attacks.
result Early fusion can suffer negative transfer under noisy settings, while late fusion is more reliable once labels stabilize.

There is a widely-accepted need to revise current forms of health-care provision, with particular interest in sensing systems in the home. Given a multiple-modality sensor platform with heterogeneous network connectivity, as is under development in the Sensor Platform for HEalthcare in Residential Environment (SPHERE) …

2017-02-04abs ↗pdf ↗