BZPEERReading, trust and collaboration for research
Menu

Discover

GraphFollow connections around a paper, topic or saved view.

Workspaces

HomePick up where your research flow left off.InboxHandle requests, replies and notifications from one place.CollectionsCurate reading lists, evidence sets and shareable dossiers.ResearchSee your private provenance graph, trail and imports.CollaborationMove from discovery into focused discussion rooms.PublishDraft, preview and publish full-text research articles.

Network

ExpertsFind specialists worth following or asking for help.CommunitiesJoin research circles organized around shared work.PartnersSee external organizations active around the same topics.

Opportunities

ListingsBrowse roles, calls and collaborations with clearer fit signals.

Account

Log inReturn to your reading and collaboration workspace.Create accountStart saving work, following people and joining teams.
Log inCreate account

Researcher profile

Xiaofang Zhou

Xiaofang Zhou contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
DatabasesArtificial IntelligenceMachine LearningComputation and LanguageCryptography and Securitycs.CYInformation RetrievalSocial and Information Networks

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
15works
0followers
8topics
4close collaborators

Actions

Decide how to stay connected

Follow researcher0

Identity and collaboration

How to connect with this researcher

Claiming links this public author record to a researcher profile and unlocks direct collaboration workflows.

Log in to claim

Direct collaboration

Open a focused conversation when the fit is right

Claim this author entity first to unlock direct invitations.

Research graph

See the researcher in context

Open full explorer

Inspect adjacent work, topics, institutions and collaborators without jumping out to a separate graph page.

Building this graph slice

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Published work

15 published item(s)

preprint2026arXiv

LiCoMemory: Lightweight and Cognitive Agentic Memory for Efficient Long-Term Reasoning

Large Language Model (LLM) agents exhibit remarkable conversational and reasoning capabilities but remain constrained by limited context windows and the lack of persistent memory. Recent efforts address these limitations via external memory architectures, often employing graph-based representations, yet most adopt flat, entangled structures that intertwine semantics with topology, leading to redundant representations, unstructured retrieval, and degraded efficiency and accuracy. To resolve these issues, we propose LiCoMemory, an end-to-end agentic memory framework for real-time updating and retrieval, which introduces CogniGraph, a lightweight hierarchical graph that utilizes entities and relations as semantic indexing layers, and employs temporal and hierarchy-aware search with integrated reranking for adaptive and coherent knowledge retrieval. Experiments on long-term dialogue benchmarks, LoCoMo and LongMemEval, show that LiCoMemory not only outperforms established baselines in temporal reasoning, multi-session consistency, and retrieval efficiency, but also notably reduces update latency. Our official code and data are available at https://github.com/EverM0re/LiCoMemory.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

R$^3$L: Reflect-then-Retry Reinforcement Learning with Language-Guided Exploration, Pivotal Credit, and Positive Amplification

Reinforcement learning drives recent advances in LLM reasoning and agentic capabilities, yet current approaches struggle with both exploration and exploitation. Exploration suffers from low success rates on difficult tasks and high costs of repeated rollouts from scratch. Exploitation suffers from coarse credit assignment and training instability: Trajectory-level rewards penalize valid prefixes for later errors, and failure-dominated groups overwhelm the few positive signals, leaving optimization without constructive direction. To this end, we propose R$^3$L, Reflect-then-Retry Reinforcement Learning with Language-Guided Exploration, Pivotal Credit, and Positive Amplification. To synthesize high-quality trajectories, R$^3$L shifts from stochastic sampling to active synthesis via reflect-then-retry, leveraging language feedback to diagnose errors, transform failed attempts into successful ones, and reduce rollout costs by restarting from identified failure points. With errors diagnosed and localized, Pivotal Credit Assignment updates only the diverging suffix where contrastive signals exist, excluding the shared prefix from gradient update. Since failures dominate on difficult tasks and reflect-then-retry produces off-policy data, risking training instability, Positive Amplification upweights successful trajectories to ensure positive signals guide the optimization process. Experiments on agentic and reasoning tasks demonstrate 5\% to 52\% relative improvements over baselines while maintaining training stability. Our code is released at https://github.com/shiweijiezero/R3L.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

SpecBlock: Block-Iterative Speculative Decoding with Dynamic Tree Drafting

Speculative decoding accelerates LLM inference by drafting a tree of candidate continuations and verifying it in one target forward. Existing drafters fall into two camps with opposite weaknesses. Autoregressive drafters such as EAGLE-3 preserve dependence along each draft path but call the drafter once per tree depth, making drafting a non-trivial share of per-iteration latency. Parallel drafters cut drafter calls by predicting multiple future positions in one forward, but each position is predicted without seeing the others, producing paths the verifier rejects. In this paper, we propose SpecBlock, a block-iterative drafter that combines path dependence with cheap drafting. Each drafter forward produces K dependent positions and we call this a block. The draft tree grows through repeated block expansions. Two mechanisms explicitly carry path dependence to keep later draft positions accurate. Within each block, a layer-wise shift carries the previous position's hidden state into every decoder layer. Across blocks, each new block can start from any position of the previous block, inheriting its hidden state to extend the path. To spend verifier budget where acceptance is likely, a co-trained rank head replaces the fixed top-k tree by allocating per-position branching during drafting. To avoid training the drafter on prefixes it never produces at inference, a valid-prefix mask drops the loss at later positions once an earlier one is wrong. Beyond static drafting, a cost-aware bandit at deployment uses free verifier feedback to update the drafter selectively, only when the expected throughput gain exceeds the update cost. Experiments show that SpecBlock improves mean speedup by 8-13% over EAGLE-3 at 44-52% of its drafting cost, and cost-aware adaptation extends this lead to 11-19%.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

A Learned Index for Exact Similarity Search in Metric Spaces

Indexing is an effective way to support efficient query processing in large databases. Recently the concept of learned index, which replaces or complements traditional index structures with machine learning models, has been actively explored to reduce storage and search costs. However, accurate and efficient similarity query processing in high-dimensional metric spaces remains to be an open challenge. In this paper, we propose a novel indexing approach called LIMS that uses data clustering, pivot-based data transformation techniques and learned indexes to support efficient similarity query processing in metric spaces. In LIMS, the underlying data is partitioned into clusters such that each cluster follows a relatively uniform data distribution. Data redistribution is achieved by utilizing a small number of pivots for each cluster. Similar data are mapped into compact regions and the mapped values are totally ordinal. Machine learning models are developed to approximate the position of each data record on disk. Efficient algorithms are designed for processing range queries and nearest neighbor queries based on LIMS, and for index maintenance with dynamic updates. Extensive experiments on real-world and synthetic datasets demonstrate the superiority of LIMS compared with traditional indexes and state-of-the-art learned indexes.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

DB-LSH: Locality-Sensitive Hashing with Query-based Dynamic Bucketing

Among many solutions to the high-dimensional approximate nearest neighbor (ANN) search problem, locality sensitive hashing (LSH) is known for its sub-linear query time and robust theoretical guarantee on query accuracy. Traditional LSH methods can generate a small number of candidates quickly from hash tables but suffer from large index sizes and hash boundary problems. Recent studies to address these issues often incur extra overhead to identify eligible candidates or remove false positives, making query time no longer sub-linear. To address this dilemma, in this paper we propose a novel LSH scheme called DB-LSH which supports efficient ANN search for large high-dimensional datasets. It organizes the projected spaces with multi-dimensional indexes rather than using fixed-width hash buckets. Our approach can significantly reduce the space cost as by avoiding the need to maintain many hash tables for different bucket sizes. During the query phase of DB-LSH, a small number of high-quality candidates can be generated efficiently by dynamically constructing query-based hypercubic buckets with the required widths through index-based window queries. For a dataset of $n$ $d$-dimensional points with approximation ratio $c$, our rigorous theoretical analysis shows that DB-LSH achieves a smaller query cost ${O(n^{ρ^*} d\log n)}$, where ${ρ^*}$ is bounded by ${1/c^α}$ while the bound is ${1/c}$ in the existing work. An extensive range of experiments on real-world data demonstrates the superiority of DB-LSH over state-of-the-art methods on both efficiency and accuracy.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Ensemble Semi-supervised Entity Alignment via Cycle-teaching

Entity alignment is to find identical entities in different knowledge graphs. Although embedding-based entity alignment has recently achieved remarkable progress, training data insufficiency remains a critical challenge. Conventional semi-supervised methods also suffer from the incorrect entity alignment in newly proposed training data. To resolve these issues, we design an iterative cycle-teaching framework for semi-supervised entity alignment. The key idea is to train multiple entity alignment models (called aligners) simultaneously and let each aligner iteratively teach its successor the proposed new entity alignment. We propose a diversity-aware alignment selection method to choose reliable entity alignment for each aligner. We also design a conflict resolution mechanism to resolve the alignment conflict when combining the new alignment of an aligner and that from its teacher. Besides, considering the influence of cycle-teaching order, we elaborately design a strategy to arrange the optimal order that can maximize the overall performance of multiple aligners. The cycle-teaching process can break the limitations of each model's learning capability and reduce the noise in new training data, leading to improved performance. Extensive experiments on benchmark datasets demonstrate the effectiveness of the proposed cycle-teaching framework, which significantly outperforms the state-of-the-art models when the training data is insufficient and the new entity alignment has much noise.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Few-Shot Semantic Relation Prediction across Heterogeneous Graphs

Semantic relation prediction aims to mine the implicit relationships between objects in heterogeneous graphs, which consist of different types of objects and different types of links. In real-world scenarios, new semantic relations constantly emerge and they typically appear with only a few labeled data. Since a variety of semantic relations exist in multiple heterogeneous graphs, the transferable knowledge can be mined from some existing semantic relations to help predict the new semantic relations with few labeled data. This inspires a novel problem of few-shot semantic relation prediction across heterogeneous graphs. However, the existing methods cannot solve this problem because they not only require a large number of labeled samples as input, but also focus on a single graph with a fixed heterogeneity. Targeting this novel and challenging problem, in this paper, we propose a Meta-learning based Graph neural network for Semantic relation prediction, named MetaGS. Firstly, MetaGS decomposes the graph structure between objects into multiple normalized subgraphs, then adopts a two-view graph neural network to capture local heterogeneous information and global structure information of these subgraphs. Secondly, MetaGS aggregates the information of these subgraphs with a hyper-prototypical network, which can learn from existing semantic relations and adapt to new semantic relations. Thirdly, using the well-initialized two-view graph neural network and hyper-prototypical network, MetaGS can effectively learn new semantic relations from different graphs while overcoming the limitation of few labeled data. Extensive experiments on three real-world datasets have demonstrated the superior performance of MetaGS over the state-of-the-art methods.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Frequency-based Randomization for Guaranteeing Differential Privacy in Spatial Trajectories

With the popularity of GPS-enabled devices, a huge amount of trajectory data has been continuously collected and a variety of location-based services have been developed that greatly benefit our daily life. However, the released trajectories also bring severe concern about personal privacy, and several recent studies have demonstrated the existence of personally-identifying information in spatial trajectories. Trajectory anonymization is nontrivial due to the trade-off between privacy protection and utility preservation. Furthermore, recovery attack has not been well studied in the current literature. To tackle these issues, we propose a frequency-based randomization model with a rigorous differential privacy guarantee for trajectory data publishing. In particular, we introduce two randomized mechanisms to perturb the local/global frequency distributions of significantly important locations in trajectories by injecting Laplace noise. We design a hierarchical indexing along with a novel search algorithm to support efficient trajectory modification, ensuring the modified trajectories satisfy the perturbed distributions without compromising privacy guarantee or data utility. Extensive experiments on a real-world trajectory dataset verify the effectiveness of our approaches in resisting individual re-identification and recovery attacks and meanwhile preserving desirable data utility as well as the feasibility in practice.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

HFUL: A Hybrid Framework for User Account Linkage across Location-Aware Social Networks

Sources of complementary information are connected when we link user accounts belonging to the same user across different platforms or devices. The expanded information promotes the development of a wide range of applications, such as cross-platform prediction, cross-platform recommendation, and advertisement. Due to the significance of user account linkage and the widespread popularization of GPS-enabled mobile devices, there are increasing research studies on linking user account with spatio-temporal data across location-aware social networks. Being different from most existing studies in this domain that only focus on the effectiveness, we propose a novel framework entitled HFUL (A Hybrid Framework for User Account Linkage across Location-Aware Social Networks), where efficiency, effectiveness, scalability, robustness, and application of user account linkage are considered. Specifically, to improve the efficiency, we develop a comprehensive index structure from the spatio-temporal perspective, and design novel pruning strategies to reduce the search space. To improve the effectiveness, a kernel density estimation-based method has been proposed to alleviate the data sparsity problem in measuring users' similarities. Additionally, we investigate the application of HFUL in terms of user prediction, time prediction, and location prediction. The extensive experiments conducted on three real-world datasets demonstrate the superiority of HFUL in terms of effectiveness, efficiency, scalability, robustness, and application compared with the state-of-the-art methods.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Informed Multi-context Entity Alignment

Entity alignment is a crucial step in integrating knowledge graphs (KGs) from multiple sources. Previous attempts at entity alignment have explored different KG structures, such as neighborhood-based and path-based contexts, to learn entity embeddings, but they are limited in capturing the multi-context features. Moreover, most approaches directly utilize the embedding similarity to determine entity alignment without considering the global interaction among entities and relations. In this work, we propose an Informed Multi-context Entity Alignment (IMEA) model to address these issues. In particular, we introduce Transformer to flexibly capture the relation, path, and neighborhood contexts, and design holistic reasoning to estimate alignment probabilities based on both embedding similarity and the relation/entity functionality. The alignment evidence obtained from holistic reasoning is further injected back into the Transformer via the proposed soft label editing to inform embedding learning. Experimental results on several benchmark datasets demonstrate the superiority of our IMEA model compared with existing state-of-the-art entity alignment methods.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Large-scale Entity Alignment via Knowledge Graph Merging, Partitioning and Embedding

Entity alignment is a crucial task in knowledge graph fusion. However, most entity alignment approaches have the scalability problem. Recent methods address this issue by dividing large KGs into small blocks for embedding and alignment learning in each. However, such a partitioning and learning process results in an excessive loss of structure and alignment. Therefore, in this work, we propose a scalable GNN-based entity alignment approach to reduce the structure and alignment loss from three perspectives. First, we propose a centrality-based subgraph generation algorithm to recall some landmark entities serving as the bridges between different subgraphs. Second, we introduce self-supervised entity reconstruction to recover entity representations from incomplete neighborhood subgraphs, and design cross-subgraph negative sampling to incorporate entities from other subgraphs in alignment learning. Third, during the inference process, we merge the embeddings of subgraphs to make a single space for alignment search. Experimental results on the benchmark OpenEA dataset and the proposed large DBpedia1M dataset verify the effectiveness of our approach.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

REPOSE: Distributed Top-k Trajectory Similarity Search with Local Reference Point Tries

Trajectory similarity computation is a fundamental component in a variety of real-world applications, such as ridesharing, road planning, and transportation optimization. Recent advances in mobile devices have enabled an unprecedented increase in the amount of available trajectory data such that efficient query processing can no longer be supported by a single machine. As a result, means of performing distributed in-memory trajectory similarity search are called for. However, existing distributed proposals suffer from either computing resource waste or are unable to support the range of similarity measures that are being used. We propose a distributed in-memory management framework called REPOSE for processing top-k trajectory similarity queries on Spark. We develop a reference point trie (RP-Trie) index to organize trajectory data for local search. In addition, we design a novel heterogeneous global partitioning strategy to eliminate load imbalance in distributed settings. We report on extensive experiments with real-world data that offer insight into the performance of the solution, and show that the solution is capable of outperforming the state-of-the-art proposals.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

EPARS: Early Prediction of At-risk Students with Online and Offline Learning Behaviors

Early prediction of students at risk (STAR) is an effective and significant means to provide timely intervention for dropout and suicide. Existing works mostly rely on either online or offline learning behaviors which are not comprehensive enough to capture the whole learning processes and lead to unsatisfying prediction performance. We propose a novel algorithm (EPARS) that could early predict STAR in a semester by modeling online and offline learning behaviors. The online behaviors come from the log of activities when students use the online learning management system. The offline behaviors derive from the check-in records of the library. Our main observations are two folds. Significantly different from good students, STAR barely have regular and clear study routines. We devised a multi-scale bag-of-regularity method to extract the regularity of learning behaviors that is robust to sparse data. Second, friends of STAR are more likely to be at risk. We constructed a co-occurrence network to approximate the underlying social network and encode the social homophily as features through network embedding. To validate the proposed algorithm, extensive experiments have been conducted among an Asian university with 15,503 undergraduate students. The results indicate EPARS outperforms baselines by 14.62% ~ 38.22% in predicting STAR.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Trajectory-Based Spatiotemporal Entity Linking

Trajectory-based spatiotemporal entity linking is to match the same moving object in different datasets based on their movement traces. It is a fundamental step to support spatiotemporal data integration and analysis. In this paper, we study the problem of spatiotemporal entity linking using effective and concise signatures extracted from their trajectories. This linking problem is formalized as a k-nearest neighbor (k-NN) query on the signatures. Four representation strategies (sequential, temporal, spatial, and spatiotemporal) and two quantitative criteria (commonality and unicity) are investigated for signature construction. A simple yet effective dimension reduction strategy is developed together with a novel indexing structure called the WR-tree to speed up the search. A number of optimization methods are proposed to improve the accuracy and robustness of the linking. Our extensive experiments on real-world datasets verify the superiority of our approach over the state-of-the-art solutions in terms of both accuracy and efficiency.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Updates-Aware Graph Pattern based Node Matching

Graph Pattern based Node Matching (GPNM) is to find all the matches of the nodes in a data graph GD based on a given pattern graph GP. GPNM has become increasingly important in many applications, e.g., group finding and expert recommendation. In real scenarios, both GP and GD are updated frequently. However, the existing GPNM methods either need to perform a new GPNM procedure from scratch to deliver the node matching results based on the updated GP and GD or incrementally perform the GPNM procedure for each of the updates, leading to low efficiency. Therefore, there is a pressing need for a new method to efficiently deliver the node matching results on the updated graphs. In this paper, we first analyze and detect the elimination relationships between the updates. Then, we construct an Elimination Hierarchy Tree (EH-Tree) to index these elimination relationships. In order to speed up the GPNM process, we propose a graph partition method and then propose a new updates-aware GPNM method, called UA-GPNM, considering the single-graph elimination relationships among the updates in a single graph of GP or GD, and also the cross-graph elimination relationships between the updates in GP and the updates in GD. UA-GPNM first delivers the GPNM result of an initial query, and then delivers the GPNM result of a subsequent query, based on the initial GPNM result and the multiple updates that occur between two queries. The experimental results on five real-world social graphs demonstrate that our proposed UA-GPNM is much more efficient than the state-of-the-art GPNM methods.

0 citations0 reviewsNo code linkedOpen access