Search Results for author:
Found 30 papers, 7 papers with code
FedFa: A Fully Asynchronous Training Paradigm for Federated Learning
We propose a full asynchronous training paradigm, called FedFa, which can guarantee model convergence and eliminate the waiting time completely for federated learning by using a few buffered results on the server for parameter updating.
FedDistill: Global Model Distillation for Local Model De-Biasing in Non-IID Federated Learning
This paper introduces FedDistill, a framework enhancing the knowledge transfer from the global model to local models, focusing on the issue of imbalanced class distribution.
Affective-NLI: Towards Accurate and Interpretable Personality Recognition in Conversation
To utilize affectivity within dialog content for accurate personality recognition, we fine-tuned a pre-trained language model specifically for emotion recognition in conversations, facilitating real-time affective annotations for utterances.
Personality-affected Emotion Generation in Dialog Systems
Therefore, we propose a new task, Personality-affected Emotion Generation, to generate emotion based on the personality given to the dialog system and further investigate a solution through the personality-affected mood transition.
Digital Twin-assisted Reinforcement Learning for Resource-aware Microservice Offloading in Edge Computing
To address this challenge, we formulate an online joint microservice offloading and bandwidth allocation problem, JMOBA, to minimize the average completion time of services.
Low-Resource Court Judgment Summarization for Common Law Systems
Current summarization datasets are insufficient to satisfy the demands of summarizing precedents across multiple jurisdictions, especially when labeled data are scarce for many jurisdictions.
Heterogeneity-aware Cross-school Electives Recommendation: a Hybrid Federated Approach
In response, we propose HFRec, a heterogeneity-aware hybrid federated recommender system designed for cross-school elective course recommendations.
Bayes-enhanced Multi-view Attention Networks for Robust POI Recommendation
To this end, we investigate a novel problem of robust POI recommendation by considering the uncertainty factors of the user check-ins, and proposes a Bayes-enhanced Multi-view Attention Network.
MGAS: Multi-Granularity Architecture Search for Trade-Off Between Model Effectiveness and Efficiency
However, existing DAS methods fail to trade off between model performance and model size.
Effective Multi-Graph Neural Networks for Illicit Account Detection on Cryptocurrency Transaction Networks
Extensive experiments, comparing against 14 existing solutions on 4 large cryptocurrency datasets of Bitcoin and Ethereum, demonstrate that DIAM consistently achieves the best performance to accurately detect illicit accounts, while being efficient.
Spatial-Temporal Data Mining for Ocean Science: Data, Methodologies, and Opportunities
Compared with typical ST data (e. g., traffic data), ST ocean data is more complicated but with unique characteristics, e. g., diverse regionality and high sparsity.
Generating a Structured Summary of Numerous Academic Papers: Dataset and Method
Existing MDS datasets usually focus on producing the structureless summary covering a few input documents.
Long Text and Multi-Table Summarization: Dataset and Method
Within a report document, the salient information can be scattered in the textual and non-textual content.
Re-GAN: Data-Efficient GANs Training via Architectural Reconfiguration
Re-GAN stabilizes the GANs models with less data and offers an alternative to the existing GANs tickets and progressive growing methods.
AdaptCL: Adaptive Continual Learning for Tackling Heterogeneity in Sequential Datasets
Managing heterogeneous datasets that vary in complexity, size, and similarity in continual learning presents a significant challenge.
Time-aware Dynamic Graph Embedding for Asynchronous Structural Evolution
Meanwhile, we treat each edge sequence as a whole and embed its ToV of the first vertex to further encode the time-sensitive information.
Hierarchical Reinforcement Learning with Opponent Modeling for Distributed Multi-agent Cooperation
To tackle the issues, we propose a hierarchical reinforcement learning approach with high-level decision-making and low-level individual control for efficient policy search.
From Multi-agent to Multi-robot: A Scalable Training and Evaluation Platform for Multi-robot Reinforcement Learning
Precisely, SMART consists of two components: 1) a simulation environment that provides a variety of complex interaction scenarios for training and 2) a real-world multi-robot system for realistic performance evaluation.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Time Series Clustering for Human Behavior Pattern Mining
Human behavior modeling deals with learning and understanding behavior patterns inherent in humans' daily routines.
Enhancing Automated Essay Scoring Performance via Fine-tuning Pre-trained Language Models with Combination of Regression and Ranking
However, to solve the AES task, previous works utilize shallow neural networks to learn essay representations and constrain calculated scores with regression loss or ranking loss, respectively.
E-Tree Learning: A Novel Decentralized Model Learning Framework for Edge AI
In this paper, we propose a novel decentralized model learning approach, namely E-Tree, which makes use of a well-designed tree structure imposed on the edge devices.
EPARS: Early Prediction of At-risk Students with Online and Offline Learning Behaviors
We propose a novel algorithm (EPARS) that could early predict STAR in a semester by modeling online and offline learning behaviors.
GGP: Glossary Guided Post-processing for Word Embedding Learning
To enhance corpus based word embedding models, researchers utilize domain knowledge to learn more distinguishable representations via joint optimization and post-processing based models.
Decode with Template: Content Preserving Sentiment Transfer
The two major challenges in existing works lie in (1) effectively disentangling the original sentiment from input sentences; and (2) preserving the semantic content while transferring the sentiment.
Generative Adversarial Networks (GANs Survey): Challenges, Solutions, and Future Directions
In this study, we perform a comprehensive survey of the advancements in GANs design and optimization solutions proposed to handle GANs challenges.
Boros: Secure Cross-Channel Transfers via Channel Hub
In this paper, we design and develop a novel off-chain system to shorten the routing path for the payment network.
Cryptography and Security
D-GAN: Deep Generative Adversarial Nets for Spatio-Temporal Prediction
However, it is still very challenging (1) to adequately learn the complex and non-linear ST relationships; (2) to model the high variations in the ST data volumes as it is inherently dynamic, changing over time (i. e., irregular) and highly influenced by many external factors, such as adverse weather, accidents, traffic control, PoI, etc.
Deep Learning for Spatio-Temporal Data Mining: A Survey
Next we classify existing literatures based on the types of ST data, the data mining tasks, and the deep learning models, followed by the applications of deep learning for STDM in different domains including transportation, climate science, human mobility, location based social network, crime analysis, and neuroscience.
Joint Topic-Semantic-aware Social Recommendation for Online Voting
JTS-MF model calculates similarity among users and votings by combining their TEWE representation and structural information of social networks, and preserves this topic-semantic-social similarity during matrix factorization.
