Search Results for author:
Found 45 papers, 22 papers with code
Data Augmentation for Few-Shot Knowledge Graph Completion from Hierarchical Perspective
To this end, we propose to solve the FKGC problem with the data augmentation technique.
Self-Improvement Programming for Temporal Knowledge Graph Question Answering
Temporal Knowledge Graph Question Answering (TKGQA) aims to answer questions with temporal intent over Temporal Knowledge Graphs (TKGs).
Exemplar-Free Class Incremental Learning via Incremental Representation
Exemplar-Free Class Incremental Learning (efCIL) aims to continuously incorporate the knowledge from new classes while retaining previously learned information, without storing any old-class exemplars (i. e., samples).
AdapTraj: A Multi-Source Domain Generalization Framework for Multi-Agent Trajectory Prediction
However, the development of multi-source domain generalization in this task presents two notable issues: (1) negative transfer; (2) inadequate modeling for external factors.
Dynamic Frequency Domain Graph Convolutional Network for Traffic Forecasting
Complex spatial dependencies in transportation networks make traffic prediction extremely challenging.
Exploring Progress in Multivariate Time Series Forecasting: Comprehensive Benchmarking and Heterogeneity Analysis
Moreover, based on the proposed BasicTS and rich heterogeneous MTS datasets, we conduct an exhaustive and reproducible performance and efficiency comparison of popular models, providing insights for researchers in selecting and designing MTS forecasting models.
E2Net: Resource-Efficient Continual Learning with Elastic Expansion Network
In E2Net, we propose Representative Network Distillation to identify the representative core subnet by assessing parameter quantity and output similarity with the working network, distilling analogous subnets within the working network to mitigate reliance on rehearsal buffers and facilitating knowledge transfer across previous tasks.
DSformer: A Double Sampling Transformer for Multivariate Time Series Long-term Prediction
Multivariate time series long-term prediction, which aims to predict the change of data in a long time, can provide references for decision-making.
HUTFormer: Hierarchical U-Net Transformer for Long-Term Traffic Forecasting
Then, we propose a novel Hierarchical U-net TransFormer (HUTFormer) to address the issues of long-term traffic forecasting.
CLIP-KD: An Empirical Study of Distilling CLIP Models
CLIP has become a promising language-supervised visual pre-training framework and achieves excellent performance over a wide range of tasks.
Categories of Response-Based, Feature-Based, and Relation-Based Knowledge Distillation
Knowledge Distillation (KD) aims to optimize a lightweight network from the perspective of over-parameterized training.
Modeling Dual Period-Varying Preferences for Takeaway Recommendation
Different from traditional recommendation, takeaway recommendation faces two main challenges: (1) Dual Interaction-Aware Preference Modeling.
Attacking Pre-trained Recommendation
Recently, a series of pioneer studies have shown the potency of pre-trained models in sequential recommendation, illuminating the path of building an omniscient unified pre-trained recommendation model for different downstream recommendation tasks.
eTag: Class-Incremental Learning with Embedding Distillation and Task-Oriented Generation
Most successful CIL methods incrementally train a feature extractor with the aid of stored exemplars, or estimate the feature distribution with the stored prototypes.
Along the Time: Timeline-traced Embedding for Temporal Knowledge Graph Completion
In order to represent the facts happening in a specific time, temporal knowledge graph (TKG) embedding approaches are put forward.
Ranked #2 on
Link Prediction
on GDELT
Joint Optimization of Active and Passive Beamforming in Multi-IRS Aided mmWave Communications
To explore the impact of IRS on the performance of mmWave communication, we investigate a multi-IRS assisted mmWave communication network and formulate a sum rate maximization problem by jointly optimizing the active and passive beamforming and the set of IRSs for assistance.
MixSKD: Self-Knowledge Distillation from Mixup for Image Recognition
MixSKD mutually distills feature maps and probability distributions between the random pair of original images and their mixup images in a meaningful way.
Spatial-Temporal Identity: A Simple yet Effective Baseline for Multivariate Time Series Forecasting
These results suggest that we can design efficient and effective models as long as they solve the indistinguishability of samples, without being limited to STGNNs.
Online Knowledge Distillation via Mutual Contrastive Learning for Visual Recognition
This enables each network to learn extra contrastive knowledge from others, leading to better feature representations, thus improving the performance of visual recognition tasks.
Pre-training Enhanced Spatial-temporal Graph Neural Network for Multivariate Time Series Forecasting
However, the patterns of time series and the dependencies between them (i. e., the temporal and spatial patterns) need to be analyzed based on long-term historical MTS data.
Ranked #2 on
Traffic Prediction
on PEMS-BAY
(using extra training data)
Decoupled Dynamic Spatial-Temporal Graph Neural Network for Traffic Forecasting
However, intuitively, traffic data encompasses two different kinds of hidden time series signals, namely the diffusion signals and inherent signals.
Ranked #3 on
Traffic Prediction
on PEMS-BAY
Localizing Semantic Patches for Accelerating Image Classification
This ensures the exact mapping from a high-level spatial location to the specific input image patch.
Cross-Image Relational Knowledge Distillation for Semantic Segmentation
Current Knowledge Distillation (KD) methods for semantic segmentation often guide the student to mimic the teacher's structured information generated from individual data samples.
Prior Gradient Mask Guided Pruning-Aware Fine-Tuning
In detail, the proposed PGMPF selectively suppresses the gradient of those ”unimportant” parameters via a prior gradient mask generated by the pruning criterion during fine-tuning.
Lifelong Generative Learning via Knowledge Reconstruction
Generative models often incur the catastrophic forgetting problem when they are used to sequentially learning multiple tasks, i. e., lifelong generative learning.
Towards Robust Knowledge Graph Embedding via Multi-task Reinforcement Learning
This will lead to low-quality and unreliable representations of KGs.
Time-Varying Channel Prediction for RIS-Assisted MU-MISO Networks via Deep Learning
To mitigate the effects of shadow fading and obstacle blocking, reconfigurable intelligent surface (RIS) has become a promising technology to improve the signal transmission quality of wireless communications by controlling the reconfigurable passive elements with less hardware cost and lower power consumption.
Convolutional Autoencoder-Based Phase Shift Feedback Compression for Intelligent Reflecting Surface-Assisted Wireless Systems
To this end, it is crucial to adjust the phases of reflecting elements of the IRS, and most of the research works focus on how to optimize/quantize the phase for different optimization objectives.
Knowledge Distillation Using Hierarchical Self-Supervision Augmented Distribution
Each auxiliary branch is guided to learn self-supervision augmented task and distill this distribution from teacher to student.
Heterogeneous Graph Neural Network with Multi-view Representation Learning
Graph neural networks for heterogeneous graph embedding is to project nodes into a low-dimensional space by exploring the heterogeneity and semantics of the heterogeneous graph.
Hierarchical Self-supervised Augmented Knowledge Distillation
We therefore adopt an alternative self-supervised augmented task to guide the network to learn the joint distribution of the original recognition task and self-supervised auxiliary task.
Ranked #20 on
Knowledge Distillation
on ImageNet
Mutual Contrastive Learning for Visual Representation Learning
We present a collaborative learning method called Mutual Contrastive Learning (MCL) for general visual representation learning.
Channel Pruning via Multi-Criteria based on Weight Dependency
However, these methods ignore a small part of weights in the next layer which disappears as the feature map is removed.
GHFP: Gradually Hard Filter Pruning
Filter pruning is widely used to reduce the computation of deep learning, enabling the deployment of Deep Neural Networks (DNNs) in resource-limited devices.
Softer Pruning, Incremental Regularization
Network pruning is widely used to compress Deep Neural Networks (DNNs).
PFGDF: Pruning Filter via Gaussian Distribution Feature for Deep Neural Networks Acceleration
Deep learning has achieved impressive results in many areas, but the deployment of edge intelligent devices is still very slow.
Multi-view Contrastive Learning for Online Knowledge Distillation
Previous Online Knowledge Distillation (OKD) often carries out mutually exchanging probability distributions, but neglects the useful representational knowledge.
Localizing Interpretable Multi-scale informative Patches Derived from Media Classification Task
Deep convolutional neural networks (CNN) always depend on wider receptive field (RF) and more complex non-linearity to achieve state-of-the-art performance, while suffering the increased difficult to interpret how relevant patches contribute the final prediction.
Towards More Efficient and Effective Inference: The Joint Decision of Multi-Participants
Existing approaches to improve the performances of convolutional neural networks by optimizing the local architectures or deepening the networks tend to increase the size of models significantly.
QMR:Q-learning based Multi-objective optimization Routing protocol for Flying Ad Hoc Networks
It is difficult for existing routing protocols for Mobile Ad Hoc Networks (MANETs) and Vehicular Ad Hoc Networks (VANETs) to adapt the high dynamics of FANETs.
DRNet: Dissect and Reconstruct the Convolutional Neural Network via Interpretable Manners
For VGG16 pre-trained on ImageNet, our method averagely gains 14. 29\% accuracy promotion for two-classes sub-tasks.
Rethinking the Number of Channels for the Convolutional Neural Network
In this paper, we propose a method for efficient automatic architecture search which is special to the widths of networks instead of the connections of neural architecture.
Gated Convolutional Networks with Hybrid Connectivity for Image Classification
We propose a simple yet effective method to reduce the redundancy of DenseNet by substantially decreasing the number of stacked modules by replacing the original bottleneck by our SMG module, which is augmented by local residual.
Ranked #60 on
Image Classification
on CIFAR-10
Multi-Objective Pruning for CNNs Using Genetic Algorithm
In this work, we propose a heuristic genetic algorithm (GA) for pruning convolutional neural networks (CNNs) according to the multi-objective trade-off among error, computation and sparsity.
EENA: Efficient Evolution of Neural Architecture
Latest algorithms for automatic neural architecture search perform remarkable but are basically directionless in search space and computational expensive in training of every intermediate architecture.
