18 citations · 50 across the 14 of their papers we have counts for
14 papers
SEAnet: A Deep Learning Architecture for Data Series Similarity Search
Qitong Wang, Themis Palpanas
A key operation for massive data series collection analysis is similarity search. According to recent studies, SAX-based indexes offer state-of-the-art performance for similarity s…
A Lightweight Sparse Interaction Network for Time Series Forecasting
Xu Zhang, Qitong Wang, Peng Wang +1
Recent work shows that linear models can outperform several transformer models in long-term time-series forecasting (TSF). However, instead of explicitly performing temporal intera…
SEMixer: Semantics Enhanced MLP-Mixer for Multiscale Mixing and Long-term Time Series Forecasting
Xu Zhang, Qitong Wang, Peng Wang +1
Modeling multiscale patterns is crucial for long-term time series forecasting (TSF). However, redundancy and noise in time series, together with semantic gaps between non-adjacent…
ParisKV: Fast and Drift-Robust KV-Cache Retrieval for Long-Context LLMs
Yanlin Qi, Xinhang Chen, Huiqiang Jiang +3
KV-cache retrieval is essential for long-context LLM inference, yet existing methods struggle with distribution drift and high latency at scale. We introduce ParisKV, a drift-robus…
Multi-period Learning for Financial Time Series Forecasting
Xu Zhang, Zhengang Huang, Yunzhi Wu +7
Time series forecasting is important in finance domain. Financial time series (TS) patterns are influenced by both short-term public opinions and medium-/long-term policy and marke…
Aokana: A GPU-Driven Voxel Rendering Framework for Open World Games
Yingrong Fang, Qitong Wang, Wei Wang
Voxels are among the most popular 3D geometric representations today. Due to their intuitiveness and ease-of-editing, voxels have been widely adopted in stylized games and low-cost…
Automated Data Quality Validation in an End-to-End GNN Framework
Sijie Dong, Soror Sahri, Themis Palpanas +1
Ensuring data quality is crucial in modern data ecosystems, especially for training or testing datasets in machine learning. Existing validation approaches rely on computing data q…
LeaFi: Data Series Indexes on Steroids with Learned Filters
Qitong Wang, Ioana Ileana, Themis Palpanas
The ever-growing collections of data series create a pressing need for efficient similarity search, which serves as the backbone for various analytics pipelines. Recent studies hav…
DumpyOS: A Data-Adaptive Multi-ary Index for Scalable Data Series Similarity Search
Zeyu Wang, Qitong Wang, Peng Wang +2
Data series indexes are necessary for managing and analyzing the increasing amounts of data series collections that are nowadays available. These indexes support both exact and app…
Enhancing Adaptive Deep Networks for Image Classification via Uncertainty-aware Decision Fusion
Xu Zhang, Zhipeng Xie, Haiyang Yu +3
Handling varying computational resources is a critical issue in modern AI applications. Adaptive deep networks, featuring the dynamic employment of multiple classifier heads among…
-Hardness: A Query Hardness Measure for Graph-Based ANN Indexes
Zeyu Wang, Qitong Wang, Xiaoxing Cheng +3
Graph-based indexes have been widely employed to accelerate approximate similarity search of high-dimensional vectors. However, the performance of graph indexes to answer different…
Dimensionality-Reduction Techniques for Approximate Nearest Neighbor Search: A Survey and Evaluation
Zeyu Wang, Haoran Xiong, Qitong Wang +4
Approximate Nearest Neighbor Search (ANNS) on high-dimensional vectors has become a fundamental and essential component in various machine learning tasks. Recently, with the rapid…
A Hierarchical Transformer Encoder to Improve Entire Neoplasm Segmentation on Whole Slide Image of Hepatocellular Carcinoma
Zhuxian Guo, Qitong Wang, Henning Müller +3
In digital histopathology, entire neoplasm segmentation on Whole Slide Image (WSI) of Hepatocellular Carcinoma (HCC) plays an important role, especially as a preprocessing filter t…
Dumpy: A Compact and Adaptive Index for Large Data Series Collections
Zeyu Wang, Qitong Wang, Peng Wang +2
Data series indexes are necessary for managing and analyzing the increasing amounts of data series collections that are nowadays available. These indexes support both exact and app…