BZPEERPapers, people, evidence and research paths
Menu

Discover

SearchFind papers, people, topics, institutions and opportunities from one place.GraphSee how papers, authors, topics and evidence connect.

Research tools

HomeContinue from the papers, people and topics that matter now.CollectionsTurn saved papers into reading lists, evidence maps and shareable context.ResearchReconstruct the path that led you from search to paper to question.CollaborationMove from a paper, topic or expert request into a focused thread.PublishCreate full-text research articles with metadata, formulas and versions.

Network

ExpertsFind specialists whose work and reviews explain why they can help.CommunitiesJoin research groups organized around papers, topics and shared evidence.

Opportunities

ListingsBrowse roles, calls and collaborations connected to real research context.

Account

Log inReturn to your saved papers, graph views and active threads.Create accountStart saving papers, building a research trail and joining teams.
Log inCreate account

Source author record

Sihong Xie

Sihong Xie appears in the imported research catalog. Authorship, coauthor and topic links are available while profile ownership is still unclaimed.

ResearcherUnclaimed source record
Machine LearningSocial and Information NetworksArtificial IntelligenceComputation and Languagephysics.soc-phComputer Science and Game TheoryCryptography and SecurityDatabasesDigital Libraries

Catalog footprint

What is connected

15works
9topics
4close collaborators

Actions

Connect this record

Log in to claim
Open graphBrowse works

Research graph

See the researcher in context

Open full explorer

Inspect adjacent papers, topics, institutions and collaborators without losing the researcher page.

Building this map preview

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

Published work

15 published item(s)

preprint2026arXiv

Attribution-Guided Continual Learning for Large Language Models

Large language models (LLMs) often suffer from catastrophic forgetting in continual learning: after learning new tasks sequentially, they perform worse on earlier tasks. Existing methods mitigate catastrophic forgetting by data replay, parameter freezing, or regularization. However, these methods lack semantic awareness of internal knowledge distribution in LLMs. As a result, they cannot distinguish parameters that should be preserved or updated. We propose an attribution-guided continual fine-tuning framework for LLMs. Our method estimates task-specific, element-wise parameter importance in each Transformer layer and uses these scores to modulate gradients. Parameters important to previous tasks receive smaller updates, while less relevant ones remain plastic for learning new tasks. Experiments on continual learning benchmarks show that our method consistently outperforms baselines, achieving better retention of old tasks while maintaining competitive performance on new tasks.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Decoupled Guidance Diffusion for Adaptive Offline Safe Reinforcement Learning

Offline safe reinforcement learning often requires policies to adapt at deployment time to safety budgets that vary across episodes or change within a single episode. While diffusion-based planners enable flexible trajectory generation, existing guidance schemes often treat reward improvement and constraint satisfaction as competing gradient objectives, which can lead to unreliable safety compliance under cost limits. We reinterpret adaptive safe trajectory generation as sampling from a constrained trajectory distribution, where the budget restricts the trajectory region, and reward shapes preferences within that region. This perspective motivates Safe Decoupled Guidance Diffusion (SDGD), which conditions classifier-free guidance on the cost limit to bias sampling toward trajectories satisfying the specified limit, while using reward-gradient guidance to refine trajectories for higher return. Because direct reward guidance can increase return while also steering samples toward trajectories with higher cumulative cost, we introduce Feasible Trajectory Relabeling (FTR) to reshape reward targets and discourage such directions. We further provide a first-order sampling-time analysis showing that FTR suppresses reward-induced cost drift under a prefix-restorative alignment condition. Extensive evaluations on the DSRL benchmark show that SDGD achieves the strongest safety compliance among baselines, satisfying the constraint on 94.7% of tasks (36/38), while obtaining the highest reward among safe methods on 21 tasks.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Geometry-Calibrated Conformal Abstention for Language Models

When language models lack relevant knowledge for a given query, they frequently generate plausible responses that can be hallucinations, rather than admitting being agnostic about the answer. Retraining models to reward admitting ignorance can lead to overly conservative behaviors and poor generalization due to scarce evaluation benchmarks. We propose a post hoc framework, Conformal Abstention (CA), adapted from conformal prediction (CP) to determine whether to abstain from answering a query. CA provides finite-sample guarantees on both the probability of participation (i.e., not abstaining) and the probability that the generated response is correct. Importantly, the abstention decision relies on prediction confidence rather than the non-conformity scores used in CP, which are intractable for open-ended generation. To better align prediction confidence with the model's ignorance, we introduce a calibration strategy using representation geometry within the model to measure knowledge involvement in shaping the response. Experiments demonstrate that we improve selective answering significantly with 75 percent conditional correctness.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

GFM4GA: Graph Foundation Model for Group Anomaly Detection

Group anomaly detection is crucial in many network applications, but faces challenges due to diverse anomaly patterns. Motivated by the success of large language models (LLMs) in natural language processing, graph foundation models (GFMs) is proposed to handle few-shot learning task with fewer labeling efforts. GFMs have been successfully applied to detection of individual anomalies but cannot be generalized to group anomalies, as group anomaly patterns must be detected as a whole and individuals in an abnormal group can look rather normal. Therefore, we propose GFM4GA, a novel graph foundation model for group anomaly detection. The pipeline is pretrained via dual-level contrastive learning based on feature-based estimation and group extraction, to capture potential group anomaly structure and feature inconsistencies. In the downstream tasks, the pipeline is finetuned in parameter-constrained and group-anomaly-proportion weighted few-shot settings, and its adaptive ability to unseen group anomalies expanded via group contexts determined by labeled anomaly neighbors. Experiments show that GFM4GA surpasses group anomaly detectors and GFMs for individual anomalies, achieving average improvements of 2.85% in AUROC and 2.55% in AUPRC.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Quantile Geometry Regularization for Distributional Reinforcement Learning

Quantile-based distributional reinforcement learning methods learn return distributions through sampled quantile regression, but their bootstrapped target quantiles may induce distorted or degenerate distribution estimates. We propose Robust Quantile-based Implicit Quantile Networks (RQIQN), a lightweight Wasserstein distributionally robust enhancement boosted from a quantile estimation perspective. We first reinterpret a snapshot of IQN loss as a collection of local empirical quantile estimation problems over sampled current fractions. We then robustify each local slot with a Wasserstein distributionally robust quantile estimation formulation, yielding a closed-form, fraction-dependent correction to the Bellman target. This correction directly addresses distributional degeneration: its median antisymmetry preserves the risk-neutral quantile average, while its monotonicity enlarges upper-lower quantile gaps and counteracts collapsed distributional spread. RQIQN thus regularizes quantile geometry without changing the underlying value objective or requiring additional sample set reconstruction. Finally, we empirically show that the proposed RQIQN outperforms other existing quantile-based distributional reinforcement learning algorithms in risk-sensitive navigation and Atari games.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Robust Conditional Conformal Prediction via Branched Normalizing Flow

Conformal prediction (CP) constructs prediction sets with marginal coverage guarantees under the assumption that the calibration and test distributions are identical. However, under distribution shift, existing approaches primarily align marginal conformal score distributions, which is sufficient to preserve marginal coverage but does not control the conditional coverage error at individual test inputs. As a consequence, CP can remain unreliable in regions where the conditional score distributions are mismatched. In this work, we bound the conditional invalidity of CP under distribution shift in terms of the Wasserstein distance between the calibration and test distributions. This result highlights the role of invertible transport in mitigating conditional coverage degradation. Motivated by this insight, we introduce Branched Normalizing Flow (BNF), a two-branch architecture that normalizes a test input to the calibration distribution and transforms the prediction set of the normalized input back to the test distribution while preserving conditional guarantees. Empirically, BNF consistently improves conditional coverage robustness on nine datasets across a wide range of confidence levels.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

SCPRM: A Schema-aware Cumulative Process Reward Model for Knowledge Graph Question Answering

Large language models excel at complex reasoning, yet evaluating their intermediate steps remains challenging. Although process reward models provide step-wise supervision, they often suffer from a risk compensation effect, where incorrect steps are offset by later correct ones, assigning high rewards to flawed reasoning paths. This issue is further exacerbated in knowledge graph (KG) reasoning, as there may exist multiple paths between the start and end entities in the KGs, and a risky step can make the reasoning path flawed. Those limitations are problematic in risk-sensitive tasks such as medical and legal KG reasoning. To address the issues, we propose a Schema-aware Cumulative Process Reward Model (SCPRM) that evaluates reasoning paths by conditioning on the reasoning prefix , and incorporating schema distance between current reasoning step and the implicit target parsed from the query, which provides cumulative and future rewards to guide the path explorations. We further integrate SCPRM into Monte Carlo Tree Search (MCTS) as SCPRM-MCTS to conduct multi-hop reasoning on KGs for question answering (QA) tasks. Across medical and legal KGQA and CWQ, SCPRM-MCTS improves the performance of Hits@k by an average of 1.18% over strong baselines, demonstrating more accurate and risk-sensitive reasoning evaluation.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Rigorous Explanation of Inference on Probabilistic Graphical Models

Probabilistic graphical models, such as Markov random fields (MRF), exploit dependencies among random variables to model a rich family of joint probability distributions. Sophisticated inference algorithms, such as belief propagation (BP), can effectively compute the marginal posteriors. Nonetheless, it is still difficult to interpret the inference outcomes for important human decision making. There is no existing method to rigorously attribute the inference outcomes to the contributing factors of the graphical models. Shapley values provide an axiomatic framework, but naively computing or even approximating the values on general graphical models is challenging and less studied. We propose GraphShapley to integrate the decomposability of Shapley values, the structure of MRFs, and the iterative nature of BP inference in a principled way for fast Shapley value computation, that 1) systematically enumerates the important contributions to the Shapley values of the explaining variables without duplicate; 2) incrementally compute the contributions without starting from scratches. We theoretically characterize GraphShapley regarding independence, equal contribution, and additivity. On nine graphs, we demonstrate that GraphShapley provides sensible and practical explanations.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Robust Spammer Detection by Nash Reinforcement Learning

Online reviews provide product evaluations for customers to make decisions. Unfortunately, the evaluations can be manipulated using fake reviews ("spams") by professional spammers, who have learned increasingly insidious and powerful spamming strategies by adapting to the deployed detectors. Spamming strategies are hard to capture, as they can be varying quickly along time, different across spammers and target products, and more critically, remained unknown in most cases. Furthermore, most existing detectors focus on detection accuracy, which is not well-aligned with the goal of maintaining the trustworthiness of product evaluations. To address the challenges, we formulate a minimax game where the spammers and spam detectors compete with each other on their practical goals that are not solely based on detection accuracy. Nash equilibria of the game lead to stable detectors that are agnostic to any mixed detection strategies. However, the game has no closed-form solution and is not differentiable to admit the typical gradient-based algorithms. We turn the game into two dependent Markov Decision Processes (MDPs) to allow efficient stochastic optimization based on multi-armed bandit and policy gradient. We experiment on three large review datasets using various state-of-the-art spamming and detection strategies and show that the optimization algorithm can reliably find an equilibrial detector that can robustly and effectively prevent spammers with any mixed spamming strategies from attaining their practical goal. Our code is available at https://github.com/YingtongDou/Nash-Detect.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

CER: Complementary Entity Recognition via Knowledge Expansion on Large Unlabeled Product Reviews

Product reviews contain a lot of useful information about product features and customer opinions. One important product feature is the complementary entity (products) that may potentially work together with the reviewed product. Knowing complementary entities of the reviewed product is very important because customers want to buy compatible products and avoid incompatible ones. In this paper, we address the problem of Complementary Entity Recognition (CER). Since no existing method can solve this problem, we first propose a novel unsupervised method to utilize syntactic dependency paths to recognize complementary entities. Then we expand category-level domain knowledge about complementary entities using only a few general seed verbs on a large amount of unlabeled reviews. The domain knowledge helps the unsupervised method to adapt to different products and greatly improves the precision of the CER task. The advantage of the proposed method is that it does not require any labeled data for training. We conducted experiments on 7 popular products with about 1200 reviews in total to demonstrate that the proposed approach is effective.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

Multi-source Hierarchical Prediction Consolidation

In big data applications such as healthcare data mining, due to privacy concerns, it is necessary to collect predictions from multiple information sources for the same instance, with raw features being discarded or withheld when aggregating multiple predictions. Besides, crowd-sourced labels need to be aggregated to estimate the ground truth of the data. Because of the imperfect predictive models or human crowdsourcing workers, noisy and conflicting information is ubiquitous and inevitable. Although state-of-the-art aggregation methods have been proposed to handle label spaces with flat structures, as the label space is becoming more and more complicated, aggregation under a label hierarchical structure becomes necessary but has been largely ignored. These label hierarchies can be quite informative as they are usually created by domain experts to make sense of highly complex label correlations for many real-world cases like protein functionality interactions or disease relationships. We propose a novel multi-source hierarchical prediction consolidation method to effectively exploits the complicated hierarchical label structures to resolve the noisy and conflicting information that inherently originates from multiple imperfect sources. We formulate the problem as an optimization problem with a closed-form solution. The proposed method captures the smoothness overall information sources as well as penalizing any consolidation result that violates the constraints derived from the label hierarchy. The hierarchical instance similarity, as well as the consolidation result, are inferred in a totally unsupervised, iterative fashion. Experimental results on both synthetic and real-world datasets show the effectiveness of the proposed method over existing alternatives.

0 citations0 reviewsNo code linkedOpen access
preprint2015arXiv

CENI: a Hybrid Framework for Efficiently Inferring Information Networks

Nowadays, the message diffusion links among users or websites drive the development of countless innovative applications. However, in reality, it is easier for us to observe the timestamps when different nodes in the network react on a message, while the connections empowering the diffusion of the message remain hidden. This motivates recent extensive studies on the network inference problem: unveiling the edges from the records of messages disseminated through them. Existing solutions are computationally expensive, which motivates us to develop an efficient two-step general framework, Clustering Embedded Network Inference (CENI). CENI integrates clustering strategies to improve the efficiency of network inference. By clustering nodes directly on the timelines of messages, we propose two naive implementations of CENI: Infection-centric CENI and Cascade-centric CENI. Additionally, we point out the critical dimension problem of CENI: instead of one-dimensional timelines, we need to first project the nodes to an Euclidean space of certain dimension before clustering. A CENI adopting clustering method on the projected space can better preserve the structure hidden in the cascades, and generate more accurately inferred links. This insight sheds light on other related work attempting to discover or utilize the latent cluster structure in the disseminated messages. By addressing the critical dimension problem, we propose the third implementation of the CENI framework: Projection-based CENI. Through extensive experiments on two real datasets, we show that the three CENI models only need around 20% $\sim$ 50% of the running time of state-of-the-art methods. Moreover, the inferred edges of Projection-based CENI preserves or even outperforms the effectiveness of state-of-the-art methods.

0 citations0 reviewsNo code linkedOpen access
preprint2014arXiv

Future Influence Ranking of Scientific Literature

Researchers or students entering a emerging research area are particularly interested in what newly published papers will be most cited and which young researchers will become influential in the future, so that they can catch the most recent advances and find valuable research directions. However, predicting the future importance of scientific articles and authors is challenging due to the dynamic nature of literature networks and evolving research topics. Different from most previous studies aiming to rank the current importance of literatures and authors, we focus on \emph{ranking the future popularity of new publications and young researchers} by proposing a unified ranking model to combine various available information. Specifically, we first propose to extract two kinds of text features, words and words co-occurrence to characterize innovative papers and authors. Then, instead of using static and un-weighted graphs, we construct time-aware weighted graphs to distinguish the various importance of links established at different time. Finally, by leveraging both the constructed text features and graphs, we propose a mutual reinforcement ranking framework called \emph{MRFRank} to rank the future importance of papers and authors simultaneously. Experimental results on the ArnetMiner dataset show that the proposed approach significantly outperforms the baselines on the metric \emph{recommendation intensity}.

0 citations0 reviewsNo code linkedOpen access
preprint2013arXiv

Latent Networks Fusion based Model for Event Recommendation in Offline Ephemeral Social Networks

With the growing amount of mobile social media, offline ephemeral social networks (OffESNs) are receiving more and more attentions. Offline ephemeral social networks (OffESNs) are the networks created ad-hoc at a specific location for a specific purpose and lasting for short period of time, relying on mobile social media such as Radio Frequency Identification (RFID) and Bluetooth devices. The primary purpose of people in the OffESNs is to acquire and share information via attending prescheduled events. Event Recommendation over this kind of networks can facilitate attendees on selecting the prescheduled events and organizers on making resource planning. However, because of lack of users preference and rating information, as well as explicit social relations, both rating based traditional recommendation methods and social-trust based recommendation methods can no longer work well to recommend events in the OffESNs. To address the challenges such as how to derive users latent preferences and social relations and how to fuse the latent information in a unified model, we first construct two heterogeneous interaction social networks, an event participation network and a physical proximity network. Then, we use them to derive users latent preferences and latent networks on social relations, including like-minded peers, co-attendees and friends. Finally, we propose an LNF (Latent Networks Fusion) model under a pairwise factor graph to infer event attendance probabilities for recommendation. Experiments on an RFID-based real conference dataset have demonstrated the effectiveness of the proposed model compared with typical solutions.

0 citations0 reviewsNo code linkedOpen access
preprint2013arXiv

Multilabel Consensus Classification

In the era of big data, a large amount of noisy and incomplete data can be collected from multiple sources for prediction tasks. Combining multiple models or data sources helps to counteract the effects of low data quality and the bias of any single model or data source, and thus can improve the robustness and the performance of predictive models. Out of privacy, storage and bandwidth considerations, in certain circumstances one has to combine the predictions from multiple models or data sources to obtain the final predictions without accessing the raw data. Consensus-based prediction combination algorithms are effective for such situations. However, current research on prediction combination focuses on the single label setting, where an instance can have one and only one label. Nonetheless, data nowadays are usually multilabeled, such that more than one label have to be predicted at the same time. Direct applications of existing prediction combination methods to multilabel settings can lead to degenerated performance. In this paper, we address the challenges of combining predictions from multiple multilabel classifiers and propose two novel algorithms, MLCM-r (MultiLabel Consensus Maximization for ranking) and MLCM-a (MLCM for microAUC). These algorithms can capture label correlations that are common in multilabel classifications, and optimize corresponding performance metrics. Experimental results on popular multilabel classification tasks verify the theoretical analysis and effectiveness of the proposed methods.

0 citations0 reviewsNo code linkedOpen access