Dual-Attention Convolution Experts for Sparse Tensor Completion

• URL: http://arxiv.org/abs/2606.21427v1
• Date: Fri, 19 Jun 2026 13:45:18 GMT
• Title: Dual-Attention Convolution Experts for Sparse Tensor Completion
• Abstract summary: We propose a novel neural tensor factorization approach, termed Dual-Attention Convolution Expert Networks with Group-Level Contrastive Learning (DCGC)<n>DCGC generates diverse non-linear alignment patterns of latent factors via a multi-channel convolution network.<n>Group-level contrastive learning strategy aggregates positive samples with identical feedback levels while separating negative samples across different levels.
• Score: 2.064997953172615
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Tensor factorization (TF) has been widely adopted for high-dimensional sparse data completion tasks. Despite significant progress, neural TF methods often struggle to capture complex cross-mode interactions and remain vulnerable to (extreme) data sparsity. To address these challenges, we propose a novel neural tensor factorization approach, termed Dual-Attention Convolution Expert Networks with Group-Level Contrastive Learning (DCGC). For the first problem, DCGC generates diverse non-linear alignment patterns of latent factors via a multi-channel convolution network, and leverages the gated dual-attention mechanism to drive the model to focus on more important output channels (i.e., convolution experts) and the aligned features. Furthermore, DCGC introduces a group-level contrastive learning strategy that aggregates positive samples with identical feedback levels while separating negative samples across different levels. This strategy injects high-quality self-supervised signals to mitigate data sparsity. Extensive experiments conducted on five datasets demonstrate that our DCGC outperforms the state-of-the-art methods in sparse tensor completion for traffic and recommendation applications. Code to reproduce the experimental results in the paper is available at https://github.com/ku1z/DCGC.

Related papers

• TopoCurate:Modeling Interaction Topology for Tool-Use Agent Training [53.93696896939915]
  Training tool-use agents typically rely on Supervised Fine-Tuning (SFT) on successful trajectories and Reinforcement Learning (RL) on pass-rate-selected tasks.<n>We propose TopoCurate, an interaction-aware framework that projects multi-trial rollouts from the same task into a unified semantic quotient topology.<n>TopoCurate achieves consistent gains of 4.2% (SFT) and 6.9% (RL) over state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-03-02T10:38:54Z)
• Scaling Up AI-Generated Image Detection via Generator-Aware Prototypes [15.99138549265524]
  Generator-Aware Prototype Learning (GAPL) is a framework that constrains representation with a structured learning paradigm.<n>GAPL achieves state-of-the-art performance, showing superior detection accuracy across a wide variety of GAN and diffusion-based generators.
  arXiv  Detail & Related papers  (2025-12-15T04:58:08Z)
• Cross-pyramid consistency regularization for semi-supervised medical image segmentation [0.4349640169711269]
  Semi-supervised learning (SSL) enables training of powerful models with the assumption of limited, carefully labelled data.<n>We propose a hybrid consistency learning approach to exploit unlabeled data for semi-supervised medical image segmentation.
  arXiv  Detail & Related papers  (2025-11-11T16:38:31Z)
• Hierarchical Self-Supervised Representation Learning for Depression Detection from Speech [51.14752758616364]
  Speech-based depression detection (SDD) is a promising, non-invasive alternative to traditional clinical assessments.<n>We propose HAREN-CTC, a novel architecture that integrates multi-layer SSL features using cross-attention within a multitask learning framework.<n>The model achieves state-of-the-art macro F1-scores of 0.81 on DAIC-WOZ and 0.82 on MODMA, outperforming prior methods across both evaluation scenarios.
  arXiv  Detail & Related papers  (2025-10-05T09:32:12Z)
• Hybrid-Collaborative Augmentation and Contrastive Sample Adaptive-Differential Awareness for Robust Attributed Graph Clustering [29.83560851166928]
  We propose a novel robust attributed graph clustering (RAGC) incorporating hybrid-collaborative augmentation (HCA) and contrastive sample adaptive-differential awareness (CSADA)<n> Comprehensive graph clustering evaluations over six benchmark datasets demonstrate the effectiveness of the proposed RAGC against several state-of-the-art CAGC methods.
  arXiv  Detail & Related papers  (2025-10-03T05:30:55Z)
• Hierarchical Identity Learning for Unsupervised Visible-Infrared Person Re-Identification [81.3063589622217]
  Unsupervised visible-infrared person re-identification (USVI-ReID) aims to learn modality-invariant image features from unlabeled cross-modal person datasets.
  arXiv  Detail & Related papers  (2025-09-15T05:10:43Z)
• Channel Fingerprint Construction for Massive MIMO: A Deep Conditional Generative Approach [65.47969413708344]
  We introduce the concept of CF twins and design a conditional generative diffusion model (CGDM)<n>We employ a variational inference technique to derive the evidence lower bound (ELBO) for the log-marginal distribution of the observed fine-grained CF conditioned on the coarse-grained CF.<n>We show that the proposed approach exhibits significant improvement in reconstruction performance compared to the baselines.
  arXiv  Detail & Related papers  (2025-05-12T01:36:06Z)
• Self-Contrastive Graph Diffusion Network [1.14219428942199]
  We propose a novel framework called the Self-Contrastive Graph Diffusion Network (SCGDN) Our framework consists of two main components: the Attentional Module (AttM) and the Diffusion Module (DiFM) Unlike existing methodologies, SCGDN is an augmentation-free approach that avoids "sampling bias" and semantic drift.
  arXiv  Detail & Related papers  (2023-07-27T04:00:23Z)
• Cluster-guided Contrastive Graph Clustering Network [53.16233290797777]
  We propose a Cluster-guided Contrastive deep Graph Clustering network (CCGC) We construct two views of the graph by designing special Siamese encoders whose weights are not shared between the sibling sub-networks. To construct semantic meaningful negative sample pairs, we regard the centers of different high-confidence clusters as negative samples.
  arXiv  Detail & Related papers  (2023-01-03T13:42:38Z)
• GraphLearner: Graph Node Clustering with Fully Learnable Augmentation [76.63963385662426]
  Contrastive deep graph clustering (CDGC) leverages the power of contrastive learning to group nodes into different clusters. We propose a Graph Node Clustering with Fully Learnable Augmentation, termed GraphLearner. It introduces learnable augmentors to generate high-quality and task-specific augmented samples for CDGC.
  arXiv  Detail & Related papers  (2022-12-07T10:19:39Z)
• Dual Clustering Co-teaching with Consistent Sample Mining for Unsupervised Person Re-Identification [13.65131691012468]
  In unsupervised person Re-ID, peer-teaching strategy leveraging two networks to facilitate training has been proven to be an effective method to deal with the pseudo label noise. This paper proposes a novel Dual Clustering Co-teaching (DCCT) approach to handle this issue. DCCT mainly exploits the features extracted by two networks to generate two sets of pseudo labels separately by clustering with different parameters.
  arXiv  Detail & Related papers  (2022-10-07T06:04:04Z)
• Mixed Graph Contrastive Network for Semi-Supervised Node Classification [63.924129159538076]
  We propose a novel graph contrastive learning method, termed Mixed Graph Contrastive Network (MGCN)<n>In our method, we improve the discriminative capability of the latent embeddings by an unperturbed augmentation strategy and a correlation reduction mechanism.<n>By combining the two settings, we extract rich supervision information from both the abundant nodes and the rare yet valuable labeled nodes for discriminative representation learning.
  arXiv  Detail & Related papers  (2022-06-06T14:26:34Z)
• Deep Attention-guided Graph Clustering with Dual Self-supervision [49.040136530379094]
  We propose a novel method, namely deep attention-guided graph clustering with dual self-supervision (DAGC) We develop a dual self-supervision solution consisting of a soft self-supervision strategy with a triplet Kullback-Leibler divergence loss and a hard self-supervision strategy with a pseudo supervision loss. Our method consistently outperforms state-of-the-art methods on six benchmark datasets.
  arXiv  Detail & Related papers  (2021-11-10T06:53:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.