New framework for manifold convolutions using toric embeddings.
problem Computational intractability of manifold convolutions.
method Isometric embeddings into tori for global manifold convolutions.
result Global definition of manifold convolutions on finite approximations.
Graph convolutional networks fail to use eigenvectors beyond the first, unlike spectral embedding.
problem Understanding when graph convolutional networks fail compared to spectral embedding.
method Presented a simple generative model to illustrate failure.
result Graph convolutional networks fail to use eigenvectors beyond the first in certain graphs.
Combines BERT and graph CNN for improved text classification.
problem Text classification problems
method Combining BERT embedding and graph convolutional neural network
result Graph CNN model performs better than classical models combined with BERT
Paper proposes KE-GCN for better graph embedding.
problem Efficiently leveraging complex graphs with heterogeneous entities and relations.
method Combines GCNs and knowledge embedding methods.
result Advantages in knowledge graph alignment and entity classification.
CTGCN learns dynamic graph embeddings preserving both local and global graph structure.
problem Learning node representations for evolving graphs while preserving both local and global graph structure.
method CTGCN uses k-core based temporal graph convolutional network to learn dynamic graph embeddings.
result CTGCN outperforms existing methods in link prediction and structural role classification.
HeteGCN improves text classification with efficient, scalable graph models.
problem Text classification with large datasets and features, especially in small labeled sets.
method HeteGCN combines PTE and TextGCN, using heterogeneous graphs and feature embeddings.
result HeteGCN achieves better performance and scalability compared to existing methods.
TransGCN combines GCNs with transformation assumptions for better link prediction in KGs.
problem Link prediction in knowledge graphs for understanding graph structure.
method Unified GCN framework with simultaneous learning of entity and relation embeddings, using transformation assumptions.
result TransGCN outperforms state-of-the-art models on FB15K-237 and WN18RR.
Unified deep framework for personalized recommendations with uncertainty.
problem Uncertainty in user preferences in recommendation systems.
method Gaussian embeddings, Monte-Carlo sampling, convolutional neural networks.
result Superior performance in recommendation accuracy compared to state-of-the-art 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.
InteractE improves link prediction in KGs by increasing feature interactions.
problem Improving link prediction in knowledge graphs by inferring missing links.
method Feature permutation, novel feature reshaping, circular convolution.
result InteractE outperforms ConvE on multiple KG datasets.
AGE improves graph embedding by smoothing features and iteratively enhancing node embeddings.
problem Challenges in attributed graph embedding, especially in preserving optimal low-pass characteristics and robustness.
method AGE, a novel framework combining Laplacian smoothing and adaptive encoding, addresses these issues.
result AGE consistently outperforms state-of-the-art methods on node clustering and link prediction tasks.
Proposes VCLANC for attributed network clustering using node and attribute embeddings.
problem Lack of mutual affinity exploitation between nodes and attributes in graph convolution.
method Dual variational auto-encoders for node and attribute embeddings, Gaussian mixture model priors, mutual distance and clustering assignment hardening losses.
result Demonstrates effectiveness on real-world attributed network datasets.
This paper presents a new semi-supervised framework with convolutional neural networks (CNNs) for text categorization. Unlike the previous approaches that rely on word embeddings, our method learns embeddings of small text regions from unlabeled data for integration into a supervised CNN. The proposed scheme for embedd…
HGCN uses hyperbolic geometry to improve graph node embeddings.
problem Distortion in Euclidean embeddings of real-world graphs.
method Derives GCN operations in hyperbolic space and maps Euclidean features to hyperbolic embeddings.
result HGCN achieves up to 63.1% error reduction in ROC AUC for link prediction.
Enhances LightGCN for credit bond recommendations with dynamic node embeddings.
problem Challenges in static embeddings for rapidly evolving user interests in finance.
method Causal graph convolution for dynamic node embeddings over chronological user-item interactions.
result Significantly enhances LightGCN performance in financial product recommendations.
This research studies affine invariance in continuous-domain convolutional neural networks.
problem Recognizing patterns and features under affine transformations in continuous domains.
method Introduces a new criterion for assessing affine invariance, embeds images into the affine Lie group, and analyzes convolution over this group.
result Extends the scope of geometrical transformations that deep-learning pipelines can handle.
ConEx learns complex embeddings for knowledge graphs, improving link prediction.
problem Predicting missing links in knowledge graphs.
method 2D convolution with Hermitian inner product of complex-valued embeddings.
result ConEx outperforms state-of-the-art methods on various benchmarks.
The computation of convolution layers in deep neural networks typically rely on high performance routines that trade space for time by using additional memory (either for packing purposes or required as part of the algorithm) to improve performance. The problems with such an approach are two-fold. First, these routines…
LNPE enhances local connections in embeddings using extended neighbor propagation.
problem Improving local connections and interactions in nonlinear dimensionality reduction.
method Inspired by GCN, LNPE extends 1-hop neighbors to n-hop neighbors in LLE.
result LNPE produces more faithful and robust embeddings with better topological and geometrical properties.
The widespread availability of electronic health records (EHRs) promises to usher in the era of personalized medicine. However, the problem of extracting useful clinical representations from longitudinal EHR data remains challenging. In this paper, we explore deep neural network models with learned medical feature embe…
Framework learns structural and functional brain network embeddings while preserving their properties.
problem Joint learning of structural and functional brain networks while preserving their intrinsic properties.
method Siamese community-preserving graph convolutional network (SCP-GCN) that learns from both structural and functional connectivity.
result Superior performance in neurological disorder analysis compared to existing methods.
PairNorm prevents node embeddings from becoming too similar in GNNs, improving performance.
problem Oversmoothing in graph neural networks (GNNs) reduces model performance with deeper layers.
method PairNorm is a normalization layer based on the graph convolution operator, preventing embeddings from becoming too similar.
result PairNorm makes deeper GNNs more robust against oversmoothing and boosts performance.
Phase2vec learns embeddings of dynamical systems without supervision.
problem Predicting the classes of 2D dynamical systems from data.
method Physics-informed convolutional network that extracts geometric features and minimizes reconstruction loss.
result Learned embeddings respect the semantics of physical systems and outperform blackbox classifiers.
Deep neural networks are composed of layers of parametrised linear operations intertwined with non linear activations. In basic models, such as the multi-layer perceptron, a linear layer operates on a simple input vector embedding of the instance being processed, and produces an output vector embedding by straight mult…
Personalized activity recognition improves performance for diverse users.
problem Poor performance of impersonal algorithms for individual users.
method Personalized activity recognition using deep embeddings from a fully convolutional neural network with triplet loss.
result Novel subject triplet loss provides the best performance overall.
Although the convolutional neural networks (CNNs) have become popular for various image processing and computer vision task recently, it remains a challenging problem to reduce the storage cost of the parameters for resource-limited platforms. In the previous studies, tensor decomposition (TD) has achieved promising co…
CNN predicts stock fluctuations using company news headlines.
problem Predicting next-day stock fluctuations based on company-specific news.
method Convolutional Neural Network (CNN) with reduced filter dimensions and multiple hidden layers. Fine-tuned word embeddings and various filter widths.
result 61.7% classification accuracy achieved using pre-learned embeddings.
Paper tackles zero-shot activity recognition using video features and text embeddings.
problem Zero-shot activity recognition with videos.
method Auto-encoder model for multimodal joint embedding, 3D convolutional action recognition for visual features, GloVe word embeddings for textual features.
result Improved zero-shot recognition results with top-n accuracy and mean Nearest Neighbor Overlap.
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.
Proposes ECLSTM for more accurate RUL estimation from time series data.
problem Predicting Remaining Useful Life (RUL) from multivariate time series data.
method Embedded Convolutional LSTM (ECLSTM) with automated hyperparameter optimization.
result ECLSTM outperforms state-of-the-art approaches on benchmark data sets.
One-hot CNN (convolutional neural network) has been shown to be effective for text categorization (Johnson & Zhang, 2015). We view it as a special case of a general framework which jointly trains a linear model with a non-linear feature generator consisting of `text region embedding + pooling'. Under this framework, we…
ALF reduces network parameters and operations by 70% and 61%, respectively, on embedded hardware.
problem Efficient deployment of deep learning models on resource-constrained hardware.
method Autoencoder-based low-rank filter-sharing technique.
result ALF achieves significant compression with minimal accuracy loss.
GCNs learn by embedding similar nodes within a class and leveraging consistent neighborhood structures.
problem Understanding how GCNs perform semi-supervised node classification on both homophilous and heterophilous graphs.
method Investigated the latent node embeddings and neighborhood structures of GCNs.
result GCNs learn by embedding similar nodes within a class and leveraging consistent neighborhood structures.
New GCNs solve graph embedding problems efficiently and interpretably.
problem Graph embedding for scalable and interpretable machine learning.
method Proposed two GCNs: CAFE-GCN and sphere-GCN, based on constrained optimization.
result Both GCNs yield good approximations of dominant eigenvectors and perform dimensionality reduction.
Monitoring the biomedical literature for cases of Adverse Drug Reactions (ADRs) is a critically important and time consuming task in pharmacovigilance. The development of computer assisted approaches to aid this process in different forms has been the subject of many recent works. One particular area that has shown pro…
Recent advancements in deep neural networks for graph-structured data have led to state-of-the-art performance on recommender system benchmarks. However, making these methods practical and scalable to web-scale recommendation tasks with billions of items and hundreds of millions of users remains a challenge. Here we de…
GEM improves recommendation by capturing complex feature interactions.
problem Capturing complex high-order interaction signals in feature-based recommendation models.
method Integrates graph convolution networks to generate high-order embeddings and combines with FM-based models.
result Significant improvement in recommendation performance over baselines.
SELD-TCN improves sound event localization and detection efficiency.
problem Efficient sound event localization and detection on embedded hardware.
method Developed a novel temporal convolutional network (TCN) architecture.
result SELD-TCN outperforms state-of-the-art SELDnet on four datasets.
Performance-aware channel pruning improves CNN on embedded GPUs.
problem Inefficient channel pruning on embedded GPUs leads to performance slowdowns.
method Evaluate higher-level libraries that analyze input characteristics for optimized code generation.
result Performance-aware pruning can achieve significant performance speedups, up to 10x.
EPNE models evolving network patterns for better predictions.
problem Capturing evolving patterns in dynamic networks.
method EPNE models temporal network evolution using causal convolutions and a temporal objective function.
result EPNE outperforms other methods in various prediction tasks.
Short-term demand forecasting models commonly combine convolutional and recurrent layers to extract complex spatiotemporal patterns in data. Long-term histories are also used to consider periodicity and seasonality patterns as time series data. In this study, we propose an efficient architecture, Temporal-Guided Networ…
We study the problem of detecting critical structures using a graph embedding model. Existing graph embedding models lack the ability to precisely detect critical structures that are specific to a task at the global scale. In this paper, we propose a novel graph embedding model, called the Ego-CNNs, that employs the eg…
Graph Convolutional Networks(GCNs) play a crucial role in graph learning tasks, however, learning graph embedding with few supervised signals is still a difficult problem. In this paper, we propose a novel training algorithm for Graph Convolutional Network, called Multi-Stage Self-Supervised(M3S) Training Algorithm, co…
CompGCN embeds nodes and relations in multi-relational graphs.
problem Handling multi-relational graphs with direction and labels.
method CompGCN uses entity-relation composition operations from KG embedding.
result CompGCN achieves superior results on node classification, link prediction, and graph classification.
Performing machine learning on structured data is complicated by the fact that such data does not have vectorial form. Therefore, multiple approaches have emerged to construct vectorial representations of structured data, from kernel and distance approaches to recurrent, recursive, and convolutional neural networks. Re…
Automates graph convolutional network design for semi-supervised node classification.
problem Designing optimal graph convolutional network architectures for semi-supervised node classification.
method An automatic process to define a problem-specific architecture based on graph structure.
result The proposed method outperforms existing methods in classification performance and network compactness.
CatGCN improves GCNs by modeling feature interactions for categorical node features.
problem Suboptimal initial node representations in GCNs due to lack of feature interaction modeling.
method Integrates explicit interaction modeling (local and global) into initial node representation learning for categorical node features.
result CatGCN enhances initial node representations through feature interaction modeling, leading to improved model performance.
Improved speech enhancement with larger neural networks using novel embeddings and biases.
problem Decreased robustness of speech enhancement models to real-world use cases.
method Frequency-positional embeddings, semi-supervised training, biased loss function.
result Better performance on real recordings with improved large neural network architecture.