23 citations · 89 across the 24 of their papers we have counts for
28 papers
VCSUM: A Versatile Chinese Meeting Summarization Dataset
Han Wu, Mingjie Zhan, Haochen Tan +3
Compared to news and chat summarization, the development of meeting summarization is hugely decelerated by the limited data. To this end, we introduce a versatile Chinese meeting s…
HySAGE: A Hybrid Static and Adaptive Graph Embedding Network for Context-Drifting Recommendations
Sichun Luo, Xinyi Zhang, Yuanzhang Xiao +1
The recent popularity of edge devices and Artificial Intelligent of Things (AIoT) has driven a new wave of contextual recommendations, such as location based Point of Interest (PoI…
Personalized Federated Recommendation via Joint Representation Learning, User Clustering, and Model Adaptation
Sichun Luo, Yuanzhang Xiao, Linqi Song
Federated recommendation applies federated learning techniques in recommendation systems to help protect user privacy by exchanging models instead of raw user data between user dev…
Zero-shot Cross-lingual Conversational Semantic Role Labeling
Han Wu, Haochen Tan, Kun Xu +3
While conversational semantic role labeling (CSRL) has shown its usefulness on Chinese conversational tasks, it is still under-explored in non-Chinese languages due to the lack of…
A Sentence is Worth 128 Pseudo Tokens: A Semantic-Aware Contrastive Learning Framework for Sentence Embeddings
Haochen Tan, Wei Shao, Han Wu +2
Contrastive learning has shown great potential in unsupervised sentence embedding tasks, e.g., SimCSE. However, We find that these existing solutions are heavily affected by superf…
EGFI: Drug-Drug Interaction Extraction and Generation with Fusion of Enriched Entity and Sentence Information
Lei Huang, Jiecong Lin, Xiangtao Li +2
The rapid growth in literature accumulates diverse and yet comprehensive biomedical knowledge hidden to be mined such as drug interactions. However, it is difficult to extract the…
Distributed Thompson Sampling
Jing Dong, Tan Li, Shaolei Ren +1
We study a cooperative multi-agent multi-armed bandits with M agents and K arms. The goal of the agents is to minimized the cumulative regret. We adapt a traditional Thompson Sampl…
Semantic Role Labeling Guided Multi-turn Dialogue ReWriter
Kun Xu, Haochen Tan, Linfeng Song +4
For multi-turn dialogue rewriting, the capacity of effectively modeling the linguistic knowledge in dialog context and getting rid of the noises is essential to improve its perform…
Federated Recommendation System via Differential Privacy
Tan Li, Linqi Song, Christina Fragouli
In this paper, we are interested in what we term the federated private bandits framework, that combines differential privacy with multi-agent bandit learning. We explore how differ…
Minimizing Age of Information with Power Constraints: Multi-user Opportunistic Scheduling in Multi-State Time-Varying Channels
Haoyue Tang, Jintao Wang, Linqi Song +1
This work is motivated by the need of collecting fresh data from power-constrained sensors in the industrial Internet of Things (IIoT) network. A recently proposed metric, the Age…
Scheduling to Minimize Age of Information in Multi-State Time-Varying Networks with Power Constraints
Haoyue Tang, Jintao Wang, Linqi Song +1
In this paper, we study how to collect fresh data in time-varying networks with power constrained users. We measure data freshness from the perspective of the central controller by…
The Tradeoff Between Privacy and Accuracy in Anomaly Detection Using Federated XGBoost
Mengwei Yang, Linqi Song, Jie Xu +2
Privacy has raised considerable concerns recently, especially with the advent of information explosion and numerous data mining techniques to explore the information inside large v…
Data Encoding for Byzantine-Resilient Distributed Optimization
Deepesh Data, Linqi Song, Suhas Diggavi
We study distributed optimization in the presence of Byzantine adversaries, where both data and computation are distributed among worker machines, of which may be corrupt.…
Regret vs. Bandwidth Trade-off for Recommendation Systems
Linqi Song, Christina Fragouli, Devavrat Shah
We consider recommendation systems that need to operate under wireless bandwidth constraints, measured as number of broadcast transmissions, and demonstrate a (tight for some insta…
Privacy in Index Coding: -Limited-Access Schemes
Mohammed Karmoose, Linqi Song, Martina Cardone +1
In the traditional index coding problem, a server employs coding to send messages to clients within the same broadcast domain. Each client already has some messages as side inf…
Dynamic Edge Caching with Popularity Drifting
Linqi Song, Jie Xu
Caching at the network edge devices such as wireless caching stations (WCS) is a key technology in the 5G network. The spatial-temporal diversity of content popularity requires dif…
Privacy in Index Coding: Improved Bounds and Coding Schemes
Mohammed Karmoose, Linqi Song, Martina Cardone +1
It was recently observed in [1], that in index coding, learning the coding matrix used by the server can pose privacy concerns: curious clients can extract information about the re…
Preserving Privacy while Broadcasting: -Limited-Access Schemes
Mohammed Karmoose, Linqi Song, Martina Cardone +1
Index coding employs coding across clients within the same broadcast domain. This typically assumes that all clients learn the coding matrix so that they can decode and retrieve th…
The Benefit of Being Flexible in Distributed Computation
Linqi Song, Sundara Rajan Srinivasavaradhan, Christina Fragouli
In wireless distributed computing, networked nodes perform intermediate computations over data placed in their memory and exchange these intermediate values to calculate function v…
A Contextual Bandit Approach for Stream-Based Active Learning
Linqi Song, Jie Xu
Contextual bandit algorithms -- a class of multi-armed bandit algorithms that exploit the contextual information -- have been shown to be effective in solving sequential decision m…
Private Broadcasting: an Index Coding Approach
Mohammed Karmoose, Linqi Song, Martina Cardone +1
Using a broadcast channel to transmit clients' data requests may impose privacy risks. In this paper, we address such privacy concerns in the index coding framework. We show how a…
A Pliable Index Coding Approach to Data Shuffling
Linqi Song, Christina Fragouli, Tianchu Zhao
A promising research area that has recently emerged, is on how to use index coding to improve the communication efficiency in distributed computing systems, especially for data shu…
A Polynomial-Time Algorithm for Pliable Index Coding
Linqi Song, Christina Fragouli
In pliable index coding, we consider a server with messages and clients where each client has as side information a subset of the messages. We seek to minimize the number o…
Stream-based Online Active Learning in a Contextual Multi-Armed Bandit Framework
Linqi Song
We study the stream-based online active learning in a contextual multi-armed bandit framework. In this framework, the reward depends on both the arm and the context. In a stream-ba…