DKN uses knowledge graphs to improve news recommendation.
problem Limited personalized news recommendations due to lack of external knowledge.
method Integrates knowledge graph representation into news recommendation using a deep knowledge-aware network (DKN).
result DKN achieves substantial gains over state-of-the-art models in click-through rate prediction.
This paper enhances language models with knowledge awareness.
problem Understanding how much knowledge pretrained language models grasp.
method Inserting explicit knowledge layers into pretraining without changing transformer architecture.
result Significantly more knowledge packed into transformer parameters.
PyKale bridges interdisciplinary ML with Python, enabling accurate predictions.
problem Cross-disciplinary barriers in machine learning.
method Knowledge-aware machine learning on graphs, images, texts, and videos.
result Enables multimodal learning and transfer learning with latest deep learning models.
KGNN-LS improves recommender systems using knowledge graphs and label smoothness.
problem Improving recommender systems through better user-item embeddings.
method KGNN-LS combines knowledge graphs, user-specific embeddings, and label smoothness regularization.
result KGNN-LS outperforms state-of-the-art baselines and handles cold-start scenarios.
Proposes dual product embedding for complementary product representation learning.
problem Detecting complementary relationships from noisy and sparse customer purchase activities.
method Knowledge-aware dual product embedding with multi-task learning and user bias terms.
result Complementary relationships are captured more accurately than simple similarity.
KGRL uses reinforcement learning with knowledge graphs for better interactive recommendation.
problem Achieving responsiveness and accuracy in dynamic user-item interactions.
method KGRL combines reinforcement learning and knowledge graphs, using a local knowledge network and attention mechanism.
result KGRL outperforms state-of-the-art methods in simulated and real-world environments.
Survey on deep learning for social network analysis.
problem Encoding social network data into useful low-dimensional representations.
method Review of neural network models for node and subgraph embeddings in various network types.
result Advancements in deep learning for complex network analysis.
RFN improves GCNs for road networks, outperforming state-of-the-art by 21%-40%.
problem Leveraging the structure of road networks effectively in machine learning tasks.
method Introducing RFN, a novel GCN specifically designed for road networks.
result RFN outperforms state-of-the-art GCNs by 21%-40% on road network tasks.
New model reconstructs networks by identifying regular components.
problem Uncovering the complexity of network structures.
method Low-rank pursuit based self-representation network model.
result Reconstructs networks and measures their regulability.
Algorithm reconstructs conserved networks from flow data.
problem Network reconstruction from flow data.
method Polynomial time algorithm exploiting graph theoretic properties and learning techniques.
result Exact network reconstruction possible for arborescence networks.
This survey clarifies dynamic network terminology and reviews GNN models for dynamic networks.
problem Ambiguity in dynamic network terminology and lack of GNN models for dynamic networks.
method Established consistent terminology and notation for dynamic networks, reviewed GNN models.
result Comprehensive survey of dynamic graph neural network models.
DCNs mimic neuronal networks for improved neural classification.
problem Lack of topological similarity between DNNs and biological neural networks.
method Developed DCNs with topologies inspired by real-world neuronal networks.
result High classification accuracy achieved by DCNs.
Study 986 diverse networks to reveal structural diversity across domains.
problem Understanding structural diversity in networks across various domains.
method Machine learning techniques (random forest, confusion matrix) on 986 real-world networks and 575 generated networks.
result Networks in the same partition have similar underlying functions, constraints, and generative mechanisms, regardless of their origins.
Network recasting transforms network architecture for faster inference.
problem Accelerate inference process through network transformation.
method Block-wise recasting of source blocks in a teacher network to target blocks in a student network.
result Transforms network architecture while preserving accuracy and reducing inference time.
Highly accurate classification of network categories achieved.
problem Distinguishing between different types of networks (e.g., social vs. web graphs).
method Used a random forest classifier on both real-world and synthetic networks.
result Achieved a 94.2% classification accuracy.
Network Lens identifies node behaviors in heterogeneous networks with high accuracy.
problem Identifying different behaviors in various parts of large heterogeneous networks.
method Zoom into network using different-sized lenses to capture local structure, weight signatures to predict node labels.
result Achieved a peak accuracy of ~42% on two networks with ~100,000 and ~1,000,000 nodes, significantly better than random.
DANE adapts network embeddings across multiple domains.
problem Learning embeddings for multiple networks without transferability.
method Graph Convolutional Network with adversarial learning.
result DANE achieves superior performance in cross-network domain adaptation.
Capsule networks are vulnerable to adversarial attacks, similar to convolutional neural networks.
problem Vulnerability of capsule networks to adversarial attacks.
method Compared capsule networks to convolutional neural networks using various adversarial attacks.
result Capsule networks are vulnerable to adversarial attacks, similar to convolutional neural networks.
Chemical networks outperform spiking neural networks in classification tasks.
problem Learning tasks with spiking neural networks require hidden layers, which are computationally expensive.
method Used deterministic mass-action kinetics to prove chemical reaction networks without hidden layers can solve tasks previously solved by spiking neural networks.
result A chemical reaction network without hidden layers outperforms a spiking neural network with hidden layers in a handwritten digit classification task.
Deep ReLU networks can be simplified to a three-layer model.
problem Understanding the behavior of deep neural networks.
method Constructive proof and algorithm to transform deep networks into shallow ones.
result Deep ReLU networks can be represented by a simpler three-layer structure.
Tackles network structure inference from time series data using GNN.
problem Inferring network structure from incomplete or no information.
method Gumbel Graph Network (GGN) model for network reconstruction and completion.
result GGN can reconstruct up to 100% network structure and infer missing parts with up to 90% accuracy.
Paper proposes algorithms for embedding directed networks with text associated nodes.
problem Learning embeddings for directed networks with text associated nodes.
method PCTADW-1 and PCTADW-2 neural network algorithms.
result Embeddings improve node classification quality on software package dependency networks.
Network embedding helps predict speed limits on incomplete Danish road network.
problem Incomplete speed limit data on Danish roads limits machine learning applications.
method Applied node2vec network embedding to Danish road network.
result Network embedding can derive useful features for predicting speed limits.
This paper explores loss landscapes of sparse neural networks, finding unique characteristics compared to dense networks.
problem Understanding the loss landscape of sparse neural networks, especially one-hidden-layer networks.
method Analyzes sparse networks with dense and sparse final layers, focusing on linear and non-linear models.
result Sparse networks can have no spurious valleys under certain conditions, but spurious valleys and minima can exist for wide sparse networks.
New approach learns latent motifs in networks for mesoscale structure analysis.
problem Understanding large-scale behavior in complex systems through mesoscale structures.
method Network dictionary learning (NDL) combining network sampling and nonnegative matrix factorization.
result Networks can be approximated using a small set of latent motifs.
The paper surveys network methods for understanding economic and financial systems.
problem Understanding interconnectedness among economic and financial entities.
method Survey of network theory, measures, and structures for economic and financial networks.
result Network methods provide tools to quantify structural properties of economic systems.
Paper links network Lasso to network flow optimization.
problem Joint clustering and optimization of networked data.
method Exploration of duality between network Lasso and network flow optimization.
result nLasso is equivalent to a minimum-cost flow problem on the data network structure.
SyNGLER generates synthetic networks efficiently while preserving key structural properties.
problem Efficiently generating realistic synthetic networks with preserved structural properties.
method SyNGLER uses latent space network models to learn and reconstruct node embeddings, then generates synthetic networks.
result SyNGLER produces synthetic networks that better preserve key network characteristics than existing approaches.
Taking inspiration from biological evolution, we explore the idea of "Can deep neural networks evolve naturally over successive generations into highly efficient deep neural networks?" by introducing the notion of synthesizing new highly efficient, yet powerful deep neural networks over successive generations via an ev…
Paper introduces method to make neural networks symmetrical.
problem Creating symmetrical neural networks for data with inherent symmetries.
method Introduces a method for modifying neural networks to enforce equivariance.
result Group convolutional neural networks are a special case of the introduced framework.
Deep networks better approximate functions with compositional structure.
problem Approximating functions with complex structures.
method Design deep networks with compositional structure, leveraging the blessing of compositionality.
result Deep networks can approximate functions better than shallow networks when the function has a compositional structure.
Secret neural networks hidden within trained models.
problem Excess capacity in neural networks allows embedding secret models.
method Novel framework for hiding secret neural networks within carrier networks.
result Detection of hidden networks is computationally infeasible.
DeepMNE learns multi-network node features for better classification.
problem Learning node features across multiple networks.
method Semisupervised autoencoder for multi-network topology.
result DeepMNE outperforms state-of-the-art methods in node classification.
Survey on learning network representations to simplify complex data analysis.
problem Complex relationships in large-scale networks are hard to analyze computationally.
method Network representation learning embeds vertices into a low-dimensional vector space to preserve topology and content.
result Improved analysis of network data through embedding techniques.
GCNs adapted for road networks improve performance on edge prediction tasks.
problem Improving machine learning on road networks for edge prediction tasks.
method Introducing Relational Fusion Network (RFN) for road networks.
result RFN outperforms state-of-the-art GCNs on road segment regression and classification tasks.
Network Lasso improves semi-supervised regression on network data.
problem Improving regression accuracy on network data with limited labeled examples.
method Applying network Lasso to semi-supervised regression problems, leveraging message passing over an empirical graph.
result Network Lasso's accuracy is linked to the existence of large network flows over the empirical graph.
Natural graph networks are a new class of graph neural networks that are more flexible and scalable.
problem Traditional graph neural networks are limited by equivariance to node permutations.
method Introduced natural graph networks, which are more flexible and scalable than conventional graph neural networks.
result Natural graph networks are as scalable as conventional message passing graph neural networks but more flexible.
Convolutional networks outperform fully-connected ones in certain tasks.
problem Understanding the computational advantage of convolutional networks over fully-connected networks.
method Demonstrated a computational advantage through a specific problem class.
result Convolutional networks can solve certain problems that fully-connected networks cannot, even with gradient descent.
Sparse neural networks can improve performance with less memory.
problem Lack of fast memory limits deep neural network performance.
method Experimented with sparse neural network topologies, including pruning-based and RadiX-Nets.
result Sparse networks achieve comparable accuracy to dense networks but suffer instability at extreme sparsity.
Random neural networks mapped to statistical physics models.
problem Design questions about neural networks.
method Mapped random neural networks to lattice models in statistical physics.
result Large scale behavior of random neural networks approximated by effective field theory.
Proposes a graph neural network for traffic forecasting in WANs.
problem Traffic forecasting challenges in WANs due to dynamic and large data volumes.
method Dynamic diffusion convolutional recurrent neural networks for multistep traffic forecasting.
result Significant improvements in forecasting accuracy compared to classical methods.
Researchers derive exact priors for finite Bayesian neural networks.
problem Understanding non-Gaussian priors in finite Bayesian neural networks.
method Analytical derivation of function space priors for finite fully-connected feedforward networks.
result Exact solutions for priors of finite networks, including Meijer G-function for linear networks and mixtures for ReLU networks.
i-cNRL learns network differences with interpretability.
problem Comparing unique network characteristics.
method Contrastive network representation learning (cNRL) integrating machine learning schemes.
result i-cNRL reveals unique network patterns with interpretability.
Deep and wide networks are shown to be equivalent in terms of their capability.
problem The relationship between the width and depth of neural networks.
method Formulated transforms to map networks, used polynomial representations.
result Deep and wide networks are quasi-equivalent with an arbitrarily small error.
New γ-capsule networks improve adversarial robustness and explainability of capsule networks.
problem Improving the robustness and explainability of capsule networks.
method Introducing γ-capsule networks with a new routing algorithm and training method. result Experimental results show γ-capsule networks are more robust and transparent. Self-teaching networks improve deep neural networks' generalization.
problem Improving deep neural networks' generalization capacity.
method Generates soft supervision labels to train lower layers, using an auxiliary loss to mimic the output layer.
result Self-teaching network achieves consistent improvements and outperforms existing methods in speech recognition tasks.
DCGANs generate drainage networks quickly from samples.
problem High computational costs in generating large numbers of drainage networks.
method DCGANs trained with connectivity-informed directional information.
result Connectivity-informed DCGANs outperform other methods in reproducing accurate drainage networks.
Quantum neural network and tensor network models outperform classical models in Japanese stock market predictions.
problem Improving stock return predictions using quantum and quantum-inspired machine learning.
method Evaluation of quantum neural network and tensor network models against classical models like linear and neural networks.
result Tensor network model outperforms classical models in Japanese stock market, including linear and neural network models.