Publications (81)
Watermarking Recommender Systems
Sixiao Zhang, Cheng Long, Wei Yuan +2
Recommender systems embody significant commercial value and represent crucial intellectual property. However, the integrity of these systems is constantly challenged by malicious a…
Wukong Framework for Not Safe For Work Detection in Text-to-Image systems
Mingrui Liu, Sixiao Zhang, Cheng Long
Text-to-Image (T2I) generation is a popular AI-generated content (AIGC) technology enabling diverse and creative image synthesis. However, some outputs may contain Not Safe For Wor…
Violation of Ericksen inequalities in lyotropic chromonic liquid crystals
Cheng Long, Jonathan V. Selinger
By analyzing elastic theory for nematic liquid crystals, we distinguish three regimes of elastic constants. In one regime, the Ericksen inequalities are satisfied, and the ground s…
Data Watermarking for Sequential Recommender Systems
Sixiao Zhang, Cheng Long, Wei Yuan +2
In the era of large foundation models, data has become a crucial component in building high-performance AI systems. As the demand for high-quality and large-scale data continues to…
Eliminating Feature Ambiguity for Few-Shot Segmentation
Qianxiong Xu, Guosheng Lin, Chen Change Loy +3
Recent advancements in few-shot segmentation (FSS) have exploited pixel-by-pixel matching between query and support features, typically based on cross attention, which selectively…
DEG: Efficient Hybrid Vector Search Using the Dynamic Edge Navigation Graph
Ziqi Yin, Jianyang Gao, Pasquale Balsebre +2
Bimodal data, such as image-text pairs, has become increasingly prevalent in the digital era. The Hybrid Vector Query (HVQ) is an effective approach for querying such data and has…
Fast Maximal Quasi-clique Enumeration: A Pruning and Branching Co-Design Approach
Kaiqiang Yu, Cheng Long
Mining cohesive subgraphs from a graph is a fundamental problem in graph data analysis. One notable cohesive structure is -quasi-clique (QC), where each vertex connects at leas…
SAMITE: Position Prompted SAM2 with Calibrated Memory for Visual Object Tracking
Qianxiong Xu, Lanyun Zhu, Chenxi Liu +4
Visual Object Tracking (VOT) is widely used in applications like autonomous driving to continuously track targets in videos. Existing methods can be roughly categorized into templa…
Unlocking the Power of SAM 2 for Few-Shot Segmentation
Qianxiong Xu, Lanyun Zhu, Xuanyi Liu +4
Few-Shot Segmentation (FSS) aims to learn class-agnostic segmentation on few classes to segment arbitrary classes, but at the risk of overfitting. To address this, some methods use…
Interaction-aware Kalman Neural Networks for Trajectory Prediction
Ce Ju, Zheng Wang, Cheng Long +2
Forecasting the motion of surrounding obstacles (vehicles, bicycles, pedestrians and etc.) benefits the on-road motion planning for intelligent and autonomous vehicles. Complex sce…
HHGT: Hierarchical Heterogeneous Graph Transformer for Heterogeneous Graph Representation Learning
Qiuyu Zhu, Liang Zhang, Qianxiong Xu +3
Despite the success of Heterogeneous Graph Neural Networks (HGNNs) in modeling real-world Heterogeneous Information Networks (HINs), challenges such as expressiveness limitations a…
Multi-Factor Spatio-Temporal Prediction based on Graph Decomposition Learning
Jiahao Ji, Jingyuan Wang, Yu Mou +1
Spatio-temporal (ST) prediction is an important and widely used technique in data mining and analytics, especially for ST data in urban systems such as transportation data. In prac…
Language-Instructed Reasoning for Group Activity Detection via Multimodal Large Language Model
Jihua Peng, Qianxiong Xu, Yichen Liu +4
Group activity detection (GAD) aims to simultaneously identify group members and categorize their collective activities within video sequences. Existing deep learning-based methods…
Mask-based Membership Inference Attacks for Retrieval-Augmented Generation
Mingrui Liu, Sixiao Zhang, Cheng Long
Retrieval-Augmented Generation (RAG) has been an effective approach to mitigate hallucinations in large language models (LLMs) by incorporating up-to-date and domain-specific knowl…
Towards advancing the earthquake forecasting by machine learning of satellite data
Pan Xiong, Lei Tong, Kun Zhang +7
Amongst the available technologies for earthquake research, remote sensing has been commonly used due to its unique features such as fast imaging and wide image-acquisition range.…
SymphonyQG: Towards Symphonious Integration of Quantization and Graph for Approximate Nearest Neighbor Search
Yutong Gou, Jianyang Gao, Yuexuan Xu +1
Approximate nearest neighbor (ANN) search in high-dimensional Euclidean space has a broad range of applications. Among existing ANN algorithms, graph-based methods have shown super…
Facet-Aware Multi-Head Mixture-of-Experts Model with Text-Enhanced Pre-training for Sequential Recommendation
Mingrui Liu, Sixiao Zhang, Cheng Long
Sequential recommendation (SR) systems excel at capturing users' dynamic preferences by leveraging their interaction histories. Most existing SR systems assign a single embedding v…
The Trojan Example: Jailbreaking LLMs through Template Filling and Unsafety Reasoning
Mingrui Liu, Sixiao Zhang, Cheng Long +1
As Large Language Models (LLMs) become integral to computing infrastructure, safety alignment serves as the primary security control preventing the generation of harmful payloads.…
A Reinforcement Learning Based R-Tree for Spatial Data Indexing in Dynamic Environments
Tu Gu, Kaiyu Feng, Gao Cong +3
Learned indices have been proposed to replace classic index structures like B-Tree with machine learning (ML) models. They require to replace both the indices and query processing…
A Survey of Generative Techniques for Spatial-Temporal Data Mining
Qianru Zhang, Haixin Wang, Cheng Long +8
This paper focuses on the integration of generative techniques into spatial-temporal data mining, considering the significant growth and diverse nature of spatial-temporal data. Wi…
Efficient Multivariate Time Series Forecasting via Calibrated Language Models with Privileged Knowledge Distillation
Chenxi Liu, Hao Miao, Qianxiong Xu +5
Multivariate time series forecasting (MTSF) endeavors to predict future observations given historical data, playing a crucial role in time series data management systems. With adva…
Points-of-Interest Relationship Inference with Spatial-enriched Graph Neural Networks
Yile Chen, Xiucheng Li, Gao Cong +5
As a fundamental component in location-based services, inferring the relationship between points-of-interests (POIs) is very critical for service providers to offer good user exper…
LLMs Meet Cross-Modal Time Series Analytics: Overview and Directions
Chenxi Liu, Hao Miao, Cheng Long +3
Large Language Models (LLMs) have emerged as a promising paradigm for time series analytics, leveraging their massive parameters and the shared sequential nature of textual and tim…
Explicit Demonstration of Geometric Frustration in Chiral Liquid Crystals
Cheng Long, Jonathan V. Selinger
Many solid materials and liquid crystals exhibit geometric frustration, meaning that they have an ideal local structure that cannot fill up space. For that reason, the global phase…
A Modular Multitask Reasoning Framework Integrating Spatio-temporal Models and LLMs
Kethmi Hirushini Hettige, Jiahao Ji, Cheng Long +3
Spatio-temporal data mining plays a pivotal role in informed decision making across diverse domains. However, existing models are often restricted to narrow tasks, lacking the capa…
BMTree: Designing, Learning, and Updating Piecewise Space-Filling Curves for Multi-Dimensional Data Indexing
Jiangneng Li, Yuang Liu, Zheng Wang +5
Space-filling curves (SFC, for short) have been widely applied to index multi-dimensional data, which first maps the data to one dimension, and then a one-dimensional indexing meth…
AirPhyNet: Harnessing Physics-Guided Neural Networks for Air Quality Prediction
Kethmi Hirushini Hettige, Jiahao Ji, Shili Xiang +3
Air quality prediction and modelling plays a pivotal role in public health and environment management, for individuals and authorities to make informed decisions. Although traditio…
PGMEL: Policy Gradient-based Generative Adversarial Network for Multimodal Entity Linking
KM Pooja, Cheng Long, Aixin Sun
The task of entity linking, which involves associating mentions with their respective entities in a knowledge graph, has received significant attention due to its numerous potentia…
GPU-Native Approximate Nearest Neighbor Search with IVF-RaBitQ: Fast Index Build and Search
Jifan Shi, Jianyang Gao, James Xia +2
Approximate nearest neighbor search (ANNS) on GPUs is gaining increasing popularity for modern retrieval and recommendation workloads that operate over massive high-dimensional vec…
On Mitigating Data Sparsity in Conversational Recommender Systems
Sixiao Zhang, Mingrui Liu, Cheng Long +4
Conversational recommender systems (CRSs) capture user preference through textual information in dialogues. However, they suffer from data sparsity on two fronts: the dialogue spac…
Fast Maximum Common Subgraph Search: A Redundancy-Reduced Backtracking Approach
Kaiqiang Yu, Kaixin Wang, Cheng Long +2
Given two input graphs, finding the largest subgraph that occurs in both, i.e., finding the maximum common subgraph, is a fundamental operator for evaluating the similarity between…
A Survey on Neural Open Information Extraction: Current Status and Future Directions
Shaowen Zhou, Bowen Yu, Aixin Sun +5
Open Information Extraction (OpenIE) facilitates domain-independent discovery of relational facts from large corpora. The technique well suits many open-world natural language unde…
Towards Cross-Modality Modeling for Time Series Analytics: A Survey in the LLM Era
Chenxi Liu, Shaowen Zhou, Qianxiong Xu +4
The proliferation of edge devices has generated an unprecedented volume of time series data across different domains, motivating various well-customized methods. Recently, Large La…
OpenSiteRec: An Open Dataset for Site Recommendation
Xinhang Li, Xiangyu Zhao, Yejing Wang +5
As a representative information retrieval task, site recommendation, which aims at predicting the optimal sites for a brand or an institution to open new branches in an automatic d…
Road Network Representation Learning: A Dual Graph based Approach
Liang Zhang, Cheng Long
Road network is a critical infrastructure powering many applications including transportation, mobility and logistics in real life. To leverage the input of a road network across t…
Coarse-grained theory for motion of solitons and skyrmions in liquid crystals
Cheng Long, Jonathan V. Selinger
Recent experiments have found that applied electric fields can induce motion of skyrmions in chiral nematic liquid crystals. To understand the magnitude and direction of the induce…
Spatial-Temporal Large Language Model for Traffic Prediction
Chenxi Liu, Sun Yang, Qianxiong Xu +4
Traffic prediction, an essential component for intelligent transportation systems, endeavours to use historical data to foresee future traffic features at specific locations. Altho…
Most Probable Densest Subgraphs
Arkaprava Saha, Xiangyu Ke, Arijit Khan +1
Computing the densest subgraph is a primitive graph operation with critical applications in detecting communities, events, and anomalies in biological, social, Web, and financial n…
Efficient and Effective Similar Subtrajectory Search with Deep Reinforcement Learning
Zheng Wang, Cheng Long, Gao Cong +1
Similar trajectory search is a fundamental problem and has been well studied over the past two decades. However, the similar subtrajectory search (SimSub) problem, aiming to return…
Maximum -Plex Search: An Alternated Reduction-and-Bound Method
Shuohao Gao, Kaiqiang Yu, Shengxin Liu +1
-plexes relax cliques by allowing each vertex to disconnect to at most vertices. Finding a maximum -plex in a graph is a fundamental operator in graph mining and has been…
RedVisor: Reasoning-Aware Prompt Injection Defense via Zero-Copy KV Cache Reuse
Mingrui Liu, Sixiao Zhang, Cheng Long +1
Large Language Models (LLMs) are increasingly vulnerable to Prompt Injection (PI) attacks, where adversarial instructions hidden within retrieved contexts hijack the model's execut…
Defense Against Model Extraction Attacks on Recommender Systems
Sixiao Zhang, Hongzhi Yin, Hongxu Chen +1
The robustness of recommender systems has become a prominent topic within the research community. Numerous adversarial attacks have been proposed, but most of them rely on extensiv…
Self-Calibrated Cross Attention Network for Few-Shot Segmentation
Qianxiong Xu, Wenting Zhao, Guosheng Lin +1
The key to the success of few-shot segmentation (FSS) lies in how to effectively utilize support samples. Most solutions compress support foreground (FG) features into prototypes,…
Reinforcement Learning Enhanced Weighted Sampling for Accurate Subgraph Counting on Fully Dynamic Graph Streams
Kaixin Wang, Cheng Long, Da Yan +2
As the popularity of graph data increases, there is a growing need to count the occurrences of subgraph patterns of interest, for a variety of applications. Many graphs are massive…
Liquid Crystal Ground States on Hyperbolic Cones
Cheng Long, David R. Nelson
We generalize the analytic theory and simulation models for liquid crystal ground states on conventional cones with positive apex Gaussian curvature and study liquid crystal ground…
KITS: Inductive Spatio-Temporal Kriging with Increment Training Strategy
Qianxiong Xu, Cheng Long, Ziyue Li +3
Sensors are commonly deployed to perceive the environment. However, due to the high cost, sensors are usually sparsely deployed. Kriging is the tailored task to infer the unobserve…
Collectively Simplifying Trajectories in a Database: A Query Accuracy Driven Approach
Zheng Wang, Cheng Long, Gao Cong +1
Increasing and massive volumes of trajectory data are being accumulated that may serve a variety of applications, such as mining popular routes or identifying ridesharing candidate…
Efficient Algorithms for Maximal k-Biplex Enumeration
Kaiqiang Yu, Cheng Long, Shengxin Liu +1
Mining maximal subgraphs with cohesive structures from a bipartite graph has been widely studied. One important cohesive structure on bipartite graphs is k-biplex, where each verte…
Geometry and mechanics of disclination lines in 3D nematic liquid crystals
Cheng Long, Xingzhou Tang, Robin L. B. Selinger +1
In 3D nematic liquid crystals, disclination lines have a range of geometric structures. Locally, they may resemble or defects in 2D nematic phases, or they may have 3…
Generative Conversational Recommender System
Sixiao Zhang, Mingrui Liu, Cheng Long
Conversational recommender systems aim to provide personalized recommendations via natural language interactions. However, existing approaches either decouple recommendation from d…
Frank-Read Mechanism in Nematic Liquid Crystals
Cheng Long, Matthew J. Deutsch, Joseph Angelo +4
In a crystalline solid under mechanical stress, a Frank-Read source is a pinned dislocation segment that repeatedly bows and detaches, generating concentric dislocation loops. We d…
Knowledge-Enhanced Conversational Recommendation via Transformer-based Sequential Modelling
Jie Zou, Aixin Sun, Cheng Long +1
In conversational recommender systems (CRSs), conversations usually involve a set of items and item-related entities or attributes, e.g., director is a related entity of a movie. T…
Billiards Sports Analytics: Datasets and Tasks
Qianru Zhang, Zheng Wang, Cheng Long +1
Nowadays, it becomes a common practice to capture some data of sports games with devices such as GPS sensors and cameras and then use the data to perform various analyses on sports…
Facet-Aware Multi-Head Mixture-of-Experts Model for Sequential Recommendation
Mingrui Liu, Sixiao Zhang, Cheng Long
Sequential recommendation (SR) systems excel at capturing users' dynamic preferences by leveraging their interaction histories. Most existing SR systems assign a single embedding v…
Representation Learning for Spatial Graphs
Zheng Wang, Ce Ju, Gao Cong +1
Recently, the topic of graph representation learning has received plenty of attention. Existing approaches usually focus on structural properties only and thus they are not suffici…
STRATA-TS: Selective Knowledge Transfer for Urban Time Series Forecasting with Retrieval-Guided Reasoning
Yue Jiang, Chenxi Liu, Yile Chen +4
Urban forecasting models often face a severe data imbalance problem: only a few cities have dense, long-span records, while many others expose short or incomplete histories. Direct…
TimeCMA: Towards LLM-Empowered Multivariate Time Series Forecasting via Cross-Modality Alignment
Chenxi Liu, Qianxiong Xu, Hao Miao +5
Multivariate time series forecasting (MTSF) aims to learn temporal dynamics among variables to forecast future time series. Existing statistical and deep learning-based methods suf…
Hybrid Mamba for Few-Shot Segmentation
Qianxiong Xu, Xuanyi Liu, Lanyun Zhu +4
Many few-shot segmentation (FSS) methods use cross attention to fuse support foreground (FG) into query features, regardless of the quadratic complexity. A recent advance Mamba can…
Generalization in Federated Learning: A Conditional Mutual Information Framework
Ziqiao Wang, Cheng Long, Yongyi Mao
Federated learning (FL) is a widely adopted privacy-preserving distributed learning framework, yet its generalization performance remains less explored compared to centralized lear…
A Study of Shape Modeling Against Noise
Cheng Long, Adrian Barbu
Shape modeling is a challenging task with many potential applications in computer vision and medical imaging. There are many shape modeling methods in the literature, each with its…
HierPromptLM: A Pure PLM-based Framework for Representation Learning on Heterogeneous Text-rich Networks
Qiuyu Zhu, Liang Zhang, Qianxiong Xu +1
Representation learning on heterogeneous text-rich networks (HTRNs), which consist of multiple types of nodes and edges with each node associated with textual information, is essen…
On Inferring User Socioeconomic Status with Mobility Records
Zheng Wang, Mingrui Liu, Cheng Long +3
When users move in a physical space (e.g., an urban space), they would have some records called mobility records (e.g., trajectories) generated by devices such as mobile phones and…
Region Embedding with Intra and Inter-View Contrastive Learning
Liang Zhang, Cheng Long, Gao Cong
Unsupervised region representation learning aims to extract dense and effective features from unlabeled urban data. While some efforts have been made for solving this problem based…
Practical and Asymptotically Optimal Quantization of High-Dimensional Vectors in Euclidean Space for Approximate Nearest Neighbor Search
Jianyang Gao, Yutong Gou, Yuexuan Xu +3
Approximate nearest neighbor (ANN) query in high-dimensional Euclidean space is a key operator in database systems. For this query, quantization is a popular family of methods deve…
High-Dimensional Approximate Nearest Neighbor Search: with Reliable and Efficient Distance Comparison Operations
Jianyang Gao, Cheng Long
Approximate K nearest neighbor (AKNN) search is a fundamental and challenging problem. We observe that in high-dimensional space, the time consumption of nearly all AKNN algorithms…
Road Extraction with Satellite Images and Partial Road Maps
Qianxiong Xu, Cheng Long, Liang Yu +1
Road extraction is a process of automatically generating road maps mainly from satellite images. Existing models all target to generate roads from the scratch despite that a large…
iRangeGraph: Improvising Range-dedicated Graphs for Range-filtering Nearest Neighbor Search
Yuexuan Xu, Jianyang Gao, Yutong Gou +2
Range-filtering approximate nearest neighbor (RFANN) search is attracting increasing attention in academia and industry. Given a set of data objects, each being a pair of a high-di…
Efficient -Clique Listing: An Edge-Oriented Branching Strategy
Kaixin Wang, Kaiqiang Yu, Cheng Long
-clique listing is a vital graph mining operator with diverse applications in various networks. The state-of-the-art algorithms all adopt a branch-and-bound (BB) framework with…
Online Anomalous Subtrajectory Detection on Road Networks with Deep Reinforcement Learning
Qianru Zhang, Zheng Wang, Cheng Long +5
Detecting anomalous trajectories has become an important task in many location-based applications. While many approaches have been proposed for this task, they suffer from various…
Maximal Biclique Enumeration with Improved Worst-Case Time Complexity Guarantee: A Partition-Oriented Strategy
Kaixin Wang, Kaiqiang Yu, Cheng Long
The maximal biclique enumeration problem in bipartite graphs is fundamental and has numerous applications in E-commerce and transaction networks. Most existing studies adopt a bran…
SubGCache: Accelerating Graph-based RAG with Subgraph-level KV Cache
Qiuyu Zhu, Liang Zhang, Qianxiong Xu +2
Graph-based retrieval-augmented generation (RAG) enables large language models (LLMs) to incorporate structured knowledge via graph retrieval as contextual input, enhancing more ac…
Liquid Crystal Ground States on Cones with Anti-Twist Boundary Conditions
Cheng Long, David R. Nelson
Geometry and topology play a fundamental role in determining pattern formation on 2D surfaces in condensed matter physics. For example, local positive Gaussian curvature of a 2D su…
Applications of the Peach-Koehler Force in Liquid Crystals
Cheng Long, Jonathan V. Selinger
In solids, external stress induces the Peach-Koehler force, which drives dislocations to move. Similarly, in liquid crystals, an external angular stress creates an analogous force,…
Maximum Degree-Based Quasi-Clique Search via an Iterative Framework
Hongbo Xia, Kaiqiang Yu, Shengxin Liu +2
Cohesive subgraph mining is a fundamental problem in graph theory with numerous real-world applications, such as social network analysis and protein-protein interaction modeling. A…
Maximal Clique Enumeration with Hybrid Branching and Early Termination
Kaixin Wang, Kaiqiang Yu, Cheng Long
Maximal clique enumeration (MCE) is crucial for tasks like community detection and biological network analysis. Existing algorithms typically adopt the branch-and-bound framework w…
RaBitQ: Quantizing High-Dimensional Vectors with a Theoretical Error Bound for Approximate Nearest Neighbor Search
Jianyang Gao, Cheng Long
Searching for approximate nearest neighbors (ANN) in the high-dimensional Euclidean space is a pivotal problem. Recently, with the help of fast SIMD-based implementations, Product…
Revisiting RaBitQ and TurboQuant: A Symmetric Comparison of Methods, Theory, and Experiments
Jianyang Gao, Yutong Gou, Yuexuan Xu +5
This technical note revisits the relationship between RaBitQ and TurboQuant under a unified comparison framework. We compare the two methods in terms of methodology, theoretical gu…
Temporal -Core Query, Revisited
Yinyu Liu, Kaiqiang Yu, Shengxin Liu +2
Querying cohesive subgraphs in temporal graphs is essential for understanding the dynamic structure of real-world networks, such as evolving communities in social platforms, shifti…
Maximum -Biplex Search on Bipartite Graphs: A Symmetric-BK Branching Approach
Kaiqiang Yu, Cheng Long
Enumerating maximal -biplexes (MBPs) of a bipartite graph has been used for applications such as fraud detection. Nevertheless, there usually exists an exponential number of MBP…
DIST: Efficient k-Clique Listing via Induced Subgraph Trie
Yehyun Nam, Jihoon Jang, Kunsoo Park +2
Listing k-cliques plays a fundamental role in various data mining tasks, such as community detection and mining of cohesive substructures. Existing algorithms for the k-clique list…
Semantic-Enhanced Representation Learning for Road Networks with Temporal Dynamics
Yile Chen, Xiucheng Li, Gao Cong +2
In this study, we introduce a novel framework called Toast for learning general-purpose representations of road networks, along with its advanced counterpart DyToast, designed to e…