Search Results for author:
Found 18 papers, 8 papers with code
GETNext: Trajectory Flow Map Enhanced Transformer for Next POI Recommendation
Instead, we propose a user-agnostic global trajectory flow map and a novel Graph Enhanced Transformer model (GETNext) to better exploit the extensive collaborative signals for a more accurate next POI prediction, and alleviate the cold start problem in the meantime.
Space Meets Time: Local Spacetime Neural Network For Traffic Flow Forecasting
We argue that such correlations are universal and play a pivotal role in traffic flow.
Adaptive Activation-based Structured Pruning
Pruning is a promising approach to compress complex deep learning models in order to deploy them on resource-constrained edge devices.
Automatic Attention Pruning: Improving and Automating Model Pruning using Attentions
Then, it proposes adaptive pruning policies for automatically meeting the pruning objectives of accuracy-critical, memory-constrained, and latency-sensitive tasks.
USER: Unsupervised Structural Entropy-based Robust Graph Neural Network
To this end, we propose USER, an unsupervised robust version of graph neural networks that is based on structural entropy.
Self-Supervised Quantization-Aware Knowledge Distillation
Quantization-aware training (QAT) and Knowledge Distillation (KD) are combined to achieve competitive performance in creating low-bit deep learning models.
BAARD: Blocking Adversarial Examples by Testing for Applicability, Reliability and Decidability
Applicability Domain defines a domain based on the known compounds and rejects any unknown compound that falls outside the domain.
A Contrastive Knowledge Transfer Framework for Model Compression and Transfer Learning
Knowledge Transfer (KT) achieves competitive performance and is widely used for image classification tasks in model compression and transfer learning.
Representing Verbs as Argument Concepts
Verbs play an important role in the understanding of natural language text.
EdgeRec: Recommender System on Edge in Mobile Taobao
Recommender system (RS) has become a crucial module in most web-scale applications.
Space Meets Time: Local Spacetime Neural Network For Traffic Flow Forecasting
We argue that such correlations are universal and play a pivotal role in traffic flow.
Iterative Activation-based Structured Pruning
To solve this problem, we propose two activation-based pruning methods, Iterative Activation-based Pruning (IAP) and Adaptive Iterative Activation-based Pruning (AIAP).
Enabling Deep Learning on Edge Devices through Filter Pruning and Knowledge Transfer
The results show that 1) our model compression method can remove up to 99. 36% parameters of WRN-28-10, while preserving a Top-1 accuracy of over 90% on CIFAR-10; 2) our knowledge transfer method enables the compressed models to achieve more than 90% accuracy on CIFAR-10 and retain good accuracy on old categories; 3) it allows the compressed models to converge within real time (three to six minutes) on the edge for incremental learning tasks; 4) it enables the model to classify unseen categories of data (78. 92% Top-1 accuracy) that it is never trained with.
D2GCLF: Document-to-Graph Classifier for Legal Document Classification
We propose a Document-to-Graph Classifier (D2GCLF), which extracts facts as relations between key participants in the law case and represents a legal document with four relation graphs.
WISK: A Workload-aware Learned Index for Spatial Keyword Queries
In this paper, we propose WISK, a learned index for spatial keyword queries, which self-adapts for optimizing querying costs given a query workload.
Poster: Self-Supervised Quantization-Aware Knowledge Distillation
Quantization-aware training (QAT) starts with a pre-trained full-precision model and performs quantization during retraining.
SGA: A Graph Augmentation Method for Signed Graph Neural Networks
Signed Graph Neural Networks (SGNNs) are vital for analyzing complex patterns in real-world signed graphs containing positive and negative links.
CSG: Curriculum Representation Learning for Signed Graph
Signed graphs are valuable for modeling complex relationships with positive and negative connections, and Signed Graph Neural Networks (SGNNs) have become crucial tools for their analysis.
