Predict bike flow at station-level with multi-graph CNNs.
problem Fine-grained bike flow prediction for station-level management.
method Multi-graph convolutional neural network model.
result Reduces 25.1% and 17.0% prediction error in New York City and Chicago.
Network analysis of human brain connectivity is critically important for understanding brain function and disease states. Embedding a brain network as a whole graph instance into a meaningful low-dimensional representation can be used to investigate disease mechanisms and inform therapeutic interventions. Moreover, by …
Bayesian framework proves thresholds for multi-graph alignment feasibility.
problem Determining when multi-graph alignment is statistically possible.
method Developed a Bayesian estimation framework over metric spaces.
result Identified thresholds for Gaussian and sparse Erdős-Rényi models.
Paper proposes a new method for population-wise matching of sulcal graphs.
problem Challenges in matching cortical fold variations across individuals.
method Population-wise multi-graph matching of sulcal graphs.
result Effectiveness of multi-graph matching in obtaining consistent labeling of sulcal basins.
DMGE learns cross-domain user behavior embeddings using multi-graphs and GNNs.
problem Data sparsity in learning large-scale item embedding from individual domain data.
method Construct multi-graphs from users' behaviors across domains, use multi-graph neural networks to learn cross-domain representation.
result DMGE outperforms state-of-the-art embedding methods in various tasks.
New framework learns labels at both bag and graph levels.
problem Learning multi-label classifiers from multi-graph bags.
method Designing scoring functions and rank-loss objective for graph and bag levels; developing sub-gradient descent algorithm.
result Superior performance over state-of-the-art algorithms.
Friend recommendation system using heterogeneous edge embeddings.
problem Inadequate performance of existing network embedding techniques on multi-graph social networks.
method Proposes a method to mine network representation exploiting heterogeneity in multi-graphs.
result Outperforms state-of-the-art baselines on Hike's social network in terms of accuracy and user satisfaction.
This paper generalizes graph representation for diverse data types.
problem Representing and querying hybrid data types in a unified way.
method Introducing a directed Tensor-Typed Multi-Graph with embeddings.
result Unified representation for visual, linguistic, and auditory data.
Paper improves risk bound for MTL with graph-dependent data.
problem Sub-optimal risk bound in multi-task learning with graph-dependent data.
method Proposes a new Bennett-type inequality and develops new Talagrand-type inequality and local fractional Rademacher complexity.
result Derives a sharper risk bound of O(nlogn). New method approximates partition function of graphical models using gauge functions and polynomials.
problem Computing the partition function of graphical models is computationally challenging.
method Combines gauge function technique with real stable polynomials to approximate partition function.
result Belief Propagation estimations in the sequence do not decrease and low-bound the partition function.
Framework combines HMM and MTGCN for spatiotemporal causal inference in clinical data.
problem Challenges in observing direct treatment effects in clinical domains.
method Integrates Hidden Markov Model and Multi Task and Multi Graph Convolutional Network for spatiotemporal data.
result Advances predictive causal inference by structurally adapting to spatiotemporal complexities.
We prove that the ends of a properly immersed simply or one connected minimal surface in H(2)xR contained in a slab of height less than πof H(2)xR, are multi-graphs. When such a surface is embedded then the ends are graphs. When embedded and simply connected, it is an entire graph.
A novel multi-view spectral clustering model fuses and clusters data views.
problem Fusing and clustering multi-view data effectively.
method Simultaneously fuses and clusters views into a single graph.
result The proposed method outperforms existing techniques.
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.
Proposes a method to improve urban spatiotemporal forecasting using multi-modal graph interaction.
problem Improving spatiotemporal forecasting in urban areas using graph convolution networks.
method Develops modality interaction mechanisms for multi-graph convolution networks to reduce generalization error.
result Proposed techniques improve prediction accuracy and model robustness compared to state-of-the-art baselines.
Unlike R3, the homogeneous spaces E(−1,τ) have a great variety of entire vertical minimal graphs. In this paper we explore conditions which guarantees that a minimal surface in E(−1,τ) is such a graph. More specifically: we introduce the definition of a generalized slab in $\mathbb{E…
In this work we study convex relaxations of quadratic optimisation problems over permutation matrices. While existing semidefinite programming approaches can achieve remarkably tight relaxations, they have the strong disadvantage that they lift the original n×n-dimensional variable to an n2×n2-d…
New approximative kernels improve PDE-G-CNNs for geometric deep learning.
problem Inaccurate approximations of exact kernels in PDE-G-CNNs.
method Developed new approximative kernels that work regardless of spatial anisotropy.
result New kernels provide better error estimates and maintain reflectional symmetries.
CNNs improve medical image classification with few samples.
problem Classifying medical images with limited training data.
method Transfer learning using CNNs, representation extraction, and a novel metric for performance prediction.
result CNN-based transfer learning outperforms feature-based methods with high correlation to test set performance.
In recent years, deep learning poses a deep technical revolution in almost every field and attracts great attentions from industry and academia. Especially, the convolutional neural network (CNN), one representative model of deep learning, achieves great successes in computer vision and natural language processing. How…
Enhances graph classification with multiple graphs.
problem Improving graph classification accuracy with multiple graphs.
method Graph fusion embedding using encoder embedding.
result The method consistently improves classification accuracy for large vertex sets.
AT-CNNs show improved shape recognition over texture recognition.
problem Understanding adversarial training's impact on CNNs' feature learning.
method Systematic qualitative and quantitative approaches to interpret AT-CNNs.
result Adversarial training reduces texture bias and improves shape recognition.
Paper learns an explainer to interpret CNN features without annotations.
problem Interpreting complex features in CNNs without labeled data.
method Unsupervised learning of an explainer to decompose and reconstruct feature maps.
result Explainer learns to reconstruct CNN features without losing information.
Paper uses CNNs to classify heart sounds from short segments.
problem Classifying heart sounds from short segments of individual beats.
method Developed a 1D-CNN and 2D-CNN ensemble for feature learning and score-level fusion.
result ECNN ensemble achieved 89.22% accuracy and 89.94% sensitivity on the PhysioNet CinC 2016 database.
Simplified Butterfly-Net2 improves CNN efficiency in solving PDEs and signal processing tasks.
problem Improving CNN efficiency in solving PDEs and signal processing tasks.
method Introducing BNet2, a simplified Butterfly-Net, and Fourier transform initialization.
result BNet2 achieves similar accuracy as CNN but with fewer parameters and improves accuracy over randomly initialized CNN.
Automates resource-efficient CNN design for IoT.
problem Designing custom CNNs for IoT applications is impractical and resource-intensive.
method Automated synthesis of resource scalable CNNs from an existing optimized baseline CNN.
result Synthesized CNNs are resource-efficient and competitive in accuracy.
2D CNNs approximate Korobov functions with near-optimal rates.
problem Approximating Korobov functions using 2D CNNs.
method Constructive approach for 2D CNNs with ReLU activations and fully connected layers.
result 2D CNNs achieve near-optimal approximation rates for Korobov functions.
Proposes interpretable filters in CNNs for object classification.
problem Learning interpretable filters in deep CNNs without additional annotations.
method Assigns each filter in a CNN to an object part during training.
result Interpretable filters are more semantically meaningful than traditional filters.
New metrics differentiate effective OOD sets for training calibrated CNNs.
problem Vanilla CNNs struggle with out-of-distribution (OOD) samples.
method Developed metrics based on generalization errors of Augmented-CNN.
result Most protective OOD sets lead to better A-CNN performance.
In image classification, visual separability between different object categories is highly uneven, and some categories are more difficult to distinguish than others. Such difficult categories demand more dedicated classifiers. However, existing deep convolutional neural networks (CNN) are trained as flat N-way classifi…
Proposes a fixed smooth convolutional layer to reduce checkerboard artifacts in CNNs.
problem Checkerboard artifacts in CNNs during upsampling and strided convolution.
method Fixed convolutional layer with adjustable smoothness, applied to four CNNs and GANs.
result Significantly improves classification performance and image generation quality.
In this paper, we address the issue of how to enhance the generalization performance of convolutional neural networks (CNN) in the early learning stage for image classification. This is motivated by real-time applications that require the generalization performance of CNN to be satisfactory within limited training time…
TinyCNN accelerates CNN models on embedded FPGA with 15x speedup.
problem Limited memory on embedded FPGAs restricts CNN performance.
method Software and hardware design tool for FPGA resource-aware CNN accelerator.
result 3% accuracy loss with 15.75x speedup on image classification.
DoPa detects various physical adversarial attacks on CNNs.
problem Vulnerability of CNNs to physical adversarial attacks.
method Interprets CNN's vulnerability, adds self-verification stage.
result Achieves 90% success rate for image attacks and 92% for audio attacks.
Study improves CNNs for audio scene classification by restricting receptive fields and adding frequency awareness.
problem Improving CNNs for robust acoustic scene classification.
method Investigated different receptive field configurations for various CNN architectures and introduced Frequency Aware CNNs.
result Several well-performing submissions to DCASE 2019 Challenge were achieved.
Simple 1D-CNN network predicts electricity loads 36 hours ahead.
problem Forecasting electricity loads for future time periods.
method Used a one-dimensional CNN with parameter scanning to optimize kernel size, filters, and dense size.
result Good forecast quality achieved with basic CNN architectures.
Morph accelerates 3D CNNs for video recognition, reducing energy consumption and improving performance.
problem Efficiently accelerating 3D CNNs for video recognition is challenging due to their large memory footprint and higher dimensionality.
method Designing a flexible accelerator called Morph that adapts to different spatial and temporal tiling strategies, and codesigning a software infrastructure to control the hardware.
result Morph achieves up to 3.4x reduction in energy consumption and up to 5.1x improvement in performance/watt compared to a baseline 3D CNN accelerator.
End-to-end trainable graph matching using improved combinatorial solvers.
problem Graph matching in deep learning.
method Combining deep learning with optimized combinatorial solvers.
result Advances state-of-the-art on deep graph matching benchmarks.
Convolutional neural networks (CNN) have achieved state of the art performance on both classification and segmentation tasks. Applying CNNs to microscopy images is challenging due to the lack of datasets labeled at the single cell level. We extend the application of CNNs to microscopy image classification and segmentat…
MBS reduces CNN model size with minimal accuracy loss.
problem Reducing CNN model size while maintaining accuracy.
method Adaptive macroblock scaling based on effective flops.
result Significant model size reduction across various CNN architectures.
Improved robustness of 1D CNNs for heart arrhythmia classification.
problem Improving the robustness of 1D CNNs for classification tasks.
method Parameterization using Cayley transform and controllability Gramian for Lipschitz-bounded CNNs.
result Improved robustness of trained Lipschitz-bounded 1D CNNs for heart arrhythmia classification.
Efficient CNN for VQA achieves similar performance to standard models.
problem Computational intensity of standard VQA models.
method Proposes a sparsely activated CNN architecture.
result Sparsely activated CNN achieves comparable performance.
Computer vision performances have been significantly improved in recent years by Convolutional Neural Networks(CNN). Currently, applications using CNN algorithms are deployed mainly on general purpose hardwares, such as CPUs, GPUs or FPGAs. However, power consumption, speed, accuracy, memory footprint, and die size sho…
This paper reports the performances of shallow word-level convolutional neural networks (CNN), our earlier work (2015), on the eight datasets with relatively large training data that were used for testing the very deep character-level CNN in Conneau et al. (2016). Our findings are as follows. The shallow word-level CNN…
Study on CNNs' learning rates and approximation capacities.
problem Learning rates and approximation capacities of CNNs.
method New approximation bound and covering number analysis for CNNs.
result Derives minimax optimal convergence rates for CNNs in various learning problems.
Graph-CNN for 3D point cloud classification tackles non-regular graph topology.
problem Classifying 3D point cloud data with non-regular graph topology.
method Developed PointGCN combining localized graph convolutions and graph downsampling.
result Achieves competitive performance on 3D object classification benchmark ModelNet.
Paper introduces zero-space memory protection for CNNs without ECC overhead.
problem Ensuring reliability of CNNs in safety-critical applications.
method In-place zero-space ECC with weight distribution-oriented training.
result First known zero-space cost memory protection for CNNs.
New CNN layer selects important channels to improve model capacity.
problem Improving model capacity under resource constraints.
method Selective allocation of channels in convolutional layers.
result New layer allows new optima that generalize better.