Search Results for author:
Found 14 papers, 6 papers with code
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
Intriguing Usage of Applicability Domain: Lessons from Cheminformatics Applied to Adversarial Learning
This problem is relieved with a technique called Applicability Domain (AD), which rejects the unsuitable compounds for the model.
EdgeRec: Recommender System on Edge in Mobile Taobao
Recommender system (RS) has become a crucial module in most web-scale applications.
Representing Verbs as Argument Concepts
Verbs play an important role in the understanding of natural language text.
