A5017352895- Time Series Analysis and Forecasting
- Advanced Text Analysis Techniques
- Anomaly Detection Techniques and Applications
- Recommender Systems and Techniques
- Neural Networks and Applications
- Stock Market Forecasting Methods
- Language, Metaphor, and Cognition
- Advanced Data Storage Technologies
- Topic Modeling
- Spam and Phishing Detection
- Advanced Bandit Algorithms Research
- Mathematics, Computing, and Information Processing
- Access Control and Trust
- Machine Learning in Healthcare
- Data Stream Mining Techniques
- Complex Systems and Time Series Analysis
- Music and Audio Processing
- Privacy-Preserving Technologies in Data
- Digital Storytelling and Education
University of Science and Technology of China
2023-2025
Deep learning-based algorithms, e.g., convolutional networks, have significantly facilitated multivariate time series classification (MTSC) task. Nevertheless, they suffer from the limitation in modeling long-range dependence due to nature of convolution operations. Recent advancements shown potential transformers capture dependence. However, it would incur severe issues, such as fixed scale representations, temporal-invariant and quadratic complexity, with directly applicable MTSC task...
Recent efforts have been dedicated to enhancing time series forecasting accuracy by introducing advanced network architectures and self-supervised pretraining strategies. Nevertheless, existing approaches still exhibit two critical drawbacks. Firstly, these methods often rely on a single dataset for training, limiting the model's generalizability due restricted scale of training data. Secondly, one-step generation schema is widely followed, which necessitates customized head overlooks...
Recent efforts have been dedicated to enhancing time series forecasting accuracy by introducing advanced network architectures and self-supervised pretraining strategies. Nevertheless, existing approaches still exhibit two critical drawbacks. Firstly, these methods often rely on a single dataset for training, limiting the model's generalizability due restricted scale of training data. Secondly, one-step generation schema is widely followed, which necessitates customized head overlooks...
For the advancements of time series classification, scrutinizing previous studies, most existing methods adopt a common learning-to-classify paradigm - classifier model tries to learn relation between sequence inputs and target label encoded by one-hot distribution. Although effective, this conceals two inherent limitations: (1) encoding categories with distribution fails reflect comparability similarity labels, (2) it is very difficult transferable across domains, which greatly hinder...
Federated recommendation (FedRec) preserves user privacy by enabling decentralized training of personalized models, but this architecture is inherently vulnerable to adversarial attacks. Significant research has been conducted on targeted attacks in FedRec systems, motivated commercial and social influence considerations. However, much work largely overlooked the differential robustness models. Moreover, our empirical findings indicate that existing attack methods achieve only limited...
This paper presents the solution of our team APEX in Meta KDD CUP 2024: CRAG Comprehensive RAG Benchmark Challenge. The benchmark addresses limitations existing QA benchmarks evaluating diverse and dynamic challenges faced by Retrieval-Augmented Generation (RAG) systems. It provides a more comprehensive assessment performance contributes to advancing research this field. We propose routing-based domain adaptive pipeline, which performs specific processing for nature question all three...
Leveraging large language models (LLMs) has garnered increasing attention and introduced novel perspectives in time series classification. However, existing approaches often overlook the crucial dynamic temporal information inherent data face challenges aligning this with textual semantics. To address these limitations, we propose HiTime, a hierarchical multi-modal model that seamlessly integrates into LLMs for multivariate classification (MTSC). Our employs feature encoder to capture...
Text-to-image generative models excel in creating images from text but struggle with ensuring alignment and consistency between outputs prompts. This paper introduces TextMatch, a novel framework that leverages multimodal optimization to address image-text discrepancies text-to-image (T2I) generation editing. TextMatch employs scoring strategy powered by large language (LLMs) visual question-answering (VQA) evaluate semantic prompts generated images. By integrating in-context learning chain...