1 citations · 1 across the 14 of their papers we have counts for
15 papers
CacheBridge: Efficient Cross-Model KV Cache Transfer
Xingyu Qu, Siyuan Lu, Zhiyu Chen +2
Sharing context between LLMs in a multi-model system requires the receiving model to prefill the shared prefix because KV caches are model-specific. Recent closed-form cross-model…
GRBench: A Comprehensive Benchmark Evaluation for Graph-relational Data Management
Zepeng Liu, Xinxin Huang, Xuanming Liu +2
Modern data-intensive applications increasingly require database systems to manage structured records and graph data. This demand gives rise to graph-relational data management, sp…
HAServe: Horizon-Aware Scheduling and Memory Co-Design for Efficient LLM Serving
Xingyu Qu, Tianhao Lin, Yiqi Li +2
Online large language model (LLM) services process requests that share context but differ in prefix structure and arrival timing. Finite capacity couples request admission and key-…
Graph-centric Cross-model Data Integration and Analytics in a Unified Multi-model Database
Zepeng Liu, Sheng Wang, Shixun Huang +6
Graph-centric cross-model data integration and analytics (GCDIA) refer to tasks that leverage the graph model as a central paradigm to integrate relevant information across heterog…
Updatable Balanced Index for Fast On-device Search with Auto-selection Model
Yushuai Ji, Sheng Wang, Zhiyu Chen +2
Diverse types of edge data, such as 2D geo-locations and 3D point clouds, are collected by sensors like lidar and GPS receivers on edge devices. On-device searches, such as k-neare…
FedAPM: Federated Learning via ADMM with Partial Model Personalization
Shengkun Zhu, Feiteng Nie, Jinshan Zeng +6
In federated learning (FL), the assumption that datasets from different devices are independent and identically distributed (i.i.d.) often does not hold due to user differences, an…
On Simplifying Large-Scale Spatial Vectors: Fast, Memory-Efficient, and Cost-Predictable k-means
Yushuai Ji, Zepeng Liu, Sheng Wang +2
The k-means algorithm can simplify large-scale spatial vectors, such as 2D geo-locations and 3D point clouds, to support fast analytics and learning. However, when processing large…
Budgeted Spatial Data Acquisition: When Coverage and Connectivity Matter
Wenzhe Yang, Shixun Huang, Sheng Wang +1
Data is undoubtedly becoming a commodity like oil, land, and labor in the 21st century. Although there have been many successful marketplaces for data trading, the existing data ma…
A Unified Approach for Multi-Granularity Search over Spatial Datasets
Wenzhe Yang, Sheng Wang, Shixun Huang +4
There has been increased interest in data search as a means to find relevant datasets or data points in data lakes and repositories. Although approaches have been proposed to suppo…
Approximate Vector Set Search Inspired by Fly Olfactory Neural System
Yiqi Li, Sheng Wang, Zhiyu Chen +2
Vector set search, an underexplored similarity search paradigm, aims to find vector sets similar to a query set. This search paradigm leverages the inherent structural alignment be…
On ADMM in Heterogeneous Federated Learning: Personalization, Robustness, and Fairness
Shengkun Zhu, Jinshan Zeng, Sheng Wang +4
Statistical heterogeneity is a root cause of tension among accuracy, fairness, and robustness of federated learning (FL), and is key in paving a path forward. Personalized FL (PFL)…
Efficient k-means with Individual Fairness via Exponential Tilting
Shengkun Zhu, Jinshan Zeng, Yuan Sun +3
In location-based resource allocation scenarios, the distances between each individual and the facility are desired to be approximately equal, thereby ensuring fairness. Individual…
Dependency Relationships-Enhanced Attentive Group Recommendation in HINs
Juntao Zhang, Sheng Wang, Zhiyu Chen +2
Recommending suitable items to a group of users, commonly referred to as the group recommendation task, is becoming increasingly urgent with the development of group activities. Th…
Joinable Search over Multi-source Spatial Datasets: Overlap, Coverage, and Efficiency
Wenzhe Yang, Sheng Wang, Zhiyu Chen +2
The search for joinable data is pivotal for numerous applications, such as data integration, data augmentation, and data analysis. Although there have been many successful joinable…
Personalized Federated Learning via ADMM with Moreau Envelope
Shengkun Zhu, Jinshan Zeng, Sheng Wang +2
Personalized federated learning (PFL) is an approach proposed to address the issue of poor convergence on heterogeneous data. However, most existing PFL frameworks require strong a…