Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks220 from public data
- A Survey on Causal Inference720
This survey provides a comprehensive review of causal inference methods under the potential outcome framework, one of the well-known causal inference frameworks, and presents the plausible applications of these methods, including the applications in advertising, recommendation, medicine, and so on.
- RecBole: Towards a Unified, Comprehensive and Efficient Framework for Recommendation Algorithms658
A unified, comprehensive and efficient recommender system library called RecBole (pronounced as [rEk'boUl@r]), which provides a unified framework to develop and reproduce recommendation algorithms for research purpose and provides a series of auxiliary functions, tools, and scripts to facilitate the use of this library.
- Resolving conflicts in heterogeneous data by truth discovery and source reliability estimation527
This paper proposes to resolve conflicts among multiple sources of heterogeneous data types by using an optimization framework where truths and source reliability are defined as two sets of unknown variables and the objective is to minimize the overall weighted deviation between the truths and the multi-source observations.
- A Survey on Truth Discovery460
This survey focuses on providing a comprehensive overview of truth discovery methods, and summarizing them from different aspects, and offers some guidelines on how to apply these approaches in application domains.
- Towards Universal Sequence Representation Learning for Recommender Systems400
A novel universal sequence representation learning approach that utilizes the associated description text of items to learn transferable representations across different recommendation scenarios, and leads to a performance improvement in a cross-platform setting, showing the strong transferability of the proposed universal SRL method.
- A confidence-aware approach for truth discovery on long-tail data358
A confidence-aware truth discovery (CATD) method to automatically detect truths from conflicting data with long-tail phenomenon is proposed, which outperforms existing state-of-the-art truth discovery approaches by successful discounting the effect of small sources.
- Representation Learning for Treatment Effect Estimation from Observational Data357
A local similarity preserved individual treatment effect (SITE) estimation method based on deep representation learning that preserves local similarity and balances data distributions simultaneously, by focusing on several hard samples in each mini-batch.
- 355
- 323
- FederatedScope-LLM: A Comprehensive Package for Fine-tuning Large Language Models in Federated Learning302
This paper builds a complete end-to-end benchmarking pipeline under real-world scenarios, automizing the processes of dataset preprocessing, federated fine-tuning execution or simulation, and performance evaluation, and provides comprehensive and off-the-shelf federated parameter-efficient fine-tuning (PEFT) algorithm implementations and versatile programming interfaces for future extension.
- Joint Slot Filling and Intent Detection via Capsule Neural Networks259
A capsule-based neural network model is proposed which accomplishes slot filling and intent detection via a dynamic routing-by-agreement schema and a re-routing schema is proposed to further synergize the slot filling performance using the inferred intent representation.
- FaitCrowd199
Experimental results on two real-world datasets show that FaitCrowd can significantly reduce the error rate of aggregation compared with the state-of-the-art multi-source aggregation approaches due to its ability of learning topical expertise from question content and collected answers.
- Federated Fine-tuning of Large Language Models under Heterogeneous Tasks and Client Resources180
FlexLoRA is introduced, a simple yet effective aggregation scheme for LLM fine-tuning, which mitigates the ``bucket effect'' in traditional FL that restricts the potential of clients with ample resources by tying them to the capabilities of the least-resourced participants.
- Unified Conversational Recommendation Policy Learning via Graph-based Reinforcement Learning169
A dynamic weighted graph based RL method to learn a policy to select the action at each conversation turn, either asking an attribute or recommending items, which significantly outperforms state-of-the-art methods but also enhances the scalability and stability of CRS.
- Cloud-Enabled Privacy-Preserving Truth Discovery in Crowd Sensing Systems168
This paper proposes a novel cloud-enabled privacy-preserving truth discovery (PPTD) framework for crowd sensing systems, which can achieve the protection of not only users' sensory data but also their reliability scores derived by the truth discovery approaches.
- FedBiOT: LLM Local Fine-tuning in Federated Learning without Full Model165
FedBiOT is introduced, a resource-efficient LLM fine-tuning approach to FL that conducts extensive experiments on LLaMA-2, empirically showing that the adapter has exceptional performance when reintegrated into the global LLM.
- Differential Privacy for Text Analytics via Natural Text Sanitization157
This paper takes a direct approach to text sanitization, to consider both sensitivity and similarity via the new local DP notion, enabling privacy-preserving natural language processing over the BERT language model with promising utility.
- Truth Discovery on Crowd Sensing of Correlated Entities154
Experiments on real-world crowd sensing applications show the advantages of the proposed method on discovering truths from conflicting information reported on correlated entities.
- 152
- On the Discovery of Evolving Truth151
This work investigates the temporal relations among both object truths and source reliability, and proposes an incremental truth discovery framework that can dynamically update object truth and source weights upon the arrival of new data.
- Crowdsourcing for Multiple-Choice Question Answering149
A crowdsourced system for playing the “Who wants to be a millionaire?” quiz show is developed and deployed, and novel weighted aggregation schemes for aggregating the answers obtained from the crowd are investigated.
- Learning to Denoise Unreliable Interactions for Graph Collaborative Filtering142
This paper presents a novel GNN-based CF model, named Robust Graph Collaborative Filtering (RGCF), to denoise unreliable interactions for recommendation and achieves significant improvement compared with baseline models.
- FederatedScope: A Flexible Federated Learning Platform for Heterogeneity126
A novel FL platform, named FederatedScope, is proposed, which employs an event-driven architecture to provide users with great flexibility to independently describe the behaviors of different participants, and enables rich types of plug-in operations and components for efficient further development.
- 125
- 123
- FederatedScope-GNN: Towards a Unified, Comprehensive and Efficient Package for Federated Graph Learning118
This paper presents the implemented package FederatedScope-GNN (FS-G), which provides a unified view for modularizing and expressing FGL algorithms, and employs FS-G to serve the FGL application in real-world E-commerce scenarios, where the attained improvements indicate great potential business benefits.
- A Correlated Topic Model Using Word Embeddings117
The proposed model enables us to exploit the additional word-level correlation information in word embeddings and directly model topic correlation in the continuous word embedding space.
- AdaBERT: Task-Adaptive BERT Compression with Differentiable Neural Architecture Search112
A novel compression method that leverages differentiable Neural Architecture Search to automatically compress BERT into task-adaptive small models for specific tasks and incorporates a task-oriented knowledge distillation loss to provide search hints and an efficiency-aware loss as search constraints, which enables a good trade-off between efficiency and effectiveness for task-adaptive BERT compression.
- Data Poisoning Attack against Knowledge Graph Embedding111
This work proposes a collection of data poisoning attack strategies, which can effectively manipulate the plausibility of arbitrary targeted facts in a knowledge graph by adding or deleting facts on the graph.
- Multi-grained Named Entity Recognition97
A novel framework for Multi-Grained Named Entity Recognition where multiple entities or entity mentions in a sentence could be non-overlapping or totally nested, MGNER detects and recognizes entities on multiple granularities and outperforms current state-of-the-art baselines.
- Data-Juicer: A One-Stop Data Processing System for Large Language Models91
A new system that can efficiently generate diverse data recipes, explore different possibilities in forming data mixtures, and evaluate their effects on model performance, and enables a timely feedback loop for both LLM pre-training and fine-tuning is built.
- Practical Data Poisoning Attack against Next-Item Recommendation90
This paper focuses on a general next-item recommendation setting and proposes a practical poisoning attack approach named LOKI against blackbox recommendation systems, which achieves better attacking performance than existing methods.
- An ontology-driven clinical decision support system (IDDAP) for infectious disease diagnosis and antibiotic prescription86
This study attempted to bridge the patient/caregiver gap by building a sophisticated application that uses artificial intelligence and machine learning computational techniques to perform data-driven decision-making at the point of primary care.
- CRSLab: An Open-Source Toolkit for Building Conversational Recommender System85
An open-source toolkit CRSLab is released, which provides a unified and extensible framework with highly-decoupled modules to develop CRSs and implements 19 models that include advanced techniques such as graph neural networks and pre-training models.
- Data Poisoning Attack against Recommender System Using Incomplete and Perturbed Data83
This paper proposes two novel adversarial attack approaches to handle the incompleteness and perturbations in user-item interaction data and proposes a bi-level optimization framework that incorporates a probabilistic generative model to find the users and items whose interaction data is sufficient and has not been significantly perturbed.
- Privacy-Preserving Truth Discovery in Crowd Sensing Systems73
This article proposes a novel privacy-preserving truth discovery (PPTD) framework, which can protect not only users’ sensory data but also their reliability scores derived by the truth discovery approaches, and proposes to parallelize PPTD with MapReduce framework.
- Meta-KD: A Meta Knowledge Distillation Framework for Language Model Compression across Domains70
This work proposes a Meta-Knowledge Distillation (Meta-KD) framework to build a meta-teacher model that captures transferable knowledge across domains and passes such knowledge to students and demonstrates the effectiveness and superiority of this framework on public multi-domain NLP tasks.
- Knowledge-aware Attentive Neural Network for Ranking Question Answer Pairs70
A context-knowledge interactive learning architecture is developed, in which a context-guided attentive convolutional neural network is designed to integrate knowledge embeddings into sentence representations and a knowledge-aware attention mechanism is presented to attend interrelations between each segments of QA pairs.
- Factual Consistency Evaluation for Text Summarization via Counterfactual Estimation67
A novel metric is proposed to evaluate the factual consistency in text summarization via counterfactual estimation, which formulates the causal relationship among the source document, the generated summary, and the language prior and provides a simple yet effective way to evaluate consistency without relying on other auxiliary tasks.
- Joint Learning of Answer Selection and Answer Summary Generation in Community Question Answering65
A question-driven pointer-generator network is designed, which exploits the correlation information between question-answer pairs to aid in attending the essential information when generating answer summaries and a new large-scale CQA corpus is constructed, WikiHowQA, which contains long answers for answer selection as well as reference summaries for answer summarization.
- A Minimax Game for Instance based Selective Transfer Learning58
This work proposes a general Minimax Game based model for selective transfer learning that outperforms the competing methods by a large margin and is shown to speed up the training process of the learning task in the target domain than traditional TL methods.
- An Efficient Two-Layer Mechanism for Privacy-Preserving Truth Discovery57
This work proposes perturbation-based mechanisms that provide users with privacy guarantees and maintain the accuracy of aggregated answers and proposes a two-layer mechanism where users are allowed to sample their own probabilities from a hyper distribution to improve the utility.
- Causal Inference Meets Machine Learning55
This tutorial introduces both traditional and state-of-the-art representation learning algorithms for treatment effect estimation, and showcases promising applications of these methods in different application domains.
- Multi-Task Learning with Multi-View Attention for Answer Selection and Knowledge Base Question Answering55
A novel multi-task learning scheme that utilizes multi-view attention learned from various perspectives to enable these tasks to interact with each other as well as learn more comprehensive sentence representations is proposed.
- Collaboratively Improving Topic Discovery and Word Embeddings by Coordinating Global and Local Contexts53
This paper empirically shows that by incorporating both global and local context, this collaborative model can not only significantly improve the performance of topic discovery over the baseline topic models, but also learn better word embeddings than the baseline word embedding models.
- 52
- Privacy-preserving Cross-domain Recommendation with Federated Graph Learning51
This article proposes a novel, as far as the authors know, federated graph learning approach for Privacy-Preserving Cross-Domain Recommendation (PPCDR) to capture users’ preferences based on distributed multi-domain data and improve recommendation performance for all domains without privacy leakage.
- Towards Differentially Private Truth Discovery for Crowd Sensing Systems50
The proposed mechanism can satisfy local differential privacy while preserving high aggregation accuracy and formally quantify utility and privacy trade-off and further verify the claim by experiments on both synthetic data and a real-world crowd sensing system.
- Toward Personalized Answer Generation in E-Commerce via Multi-perspective Preference Modeling49
Experimental results on real-world E-commerce QA datasets demonstrate that the proposed Personalized Answer GEneration method outperforms existing methods by generating informative and customized answers and show that answer generation in E-Commerce can benefit from personalization.
- 47
- FS-REAL: Towards Real-World Cross-Device Federated Learning45
An efficient and scalable prototyping system for real-world cross-device FL, FS-REAL, which supports heterogeneous device runtime, contains parallelism and robustness enhanced FL server, and provides implementations and extensibility for advanced FL utility features such as personalization, communication compression and asynchronous aggregation is proposed.
- 44
- CBN: Constructing a clinical Bayesian network based on data from the electronic medical record43
This study demonstrates that the direct and automated construction of a high-quality health topology and ontology from medical records is feasible and is reproducible.
- Multi-View Time Series Classification: A Discriminative Bilinear Projection Approach43
This work proposes a novel approach, named Multi-view Discriminative Bilinear Projections (MDBP), for extracting discriminative features from multi-view m.t.s. data, and greatly improves the classification accuracy due to the full exploration of multi- view streaming data.
- Knowledge as A Bridge: Improving Cross-domain Answer Selection with External Knowledge35
This paper proposes Knowledge-aware Attentive Network (KAN), a transfer learning framework for cross-domain answer selection, which uses the knowledge base as a bridge to enable knowledge transfer from the source domain to the target domains.
- FIVES: Feature Interaction Via Edge Search for Large-Scale Tabular Data33
This work proposes a novel method named Feature Interaction Via Edge Search (FIVES), which formulates the task of interactive feature generation as searching for edges on the defined feature graph and instantiates this search strategy by optimizing both a dedicated graph neural network (GNN) and the adjacency tensor associated with thedefined feature graph.
- Extracting Relation Descriptors with Conditional Random Fields32
This paper proposes two modifications to linear-chain CRFs, namely, reducing the space of possible label sequences and introducing long-range features, and finds that both modifications can significantly improve the performance for this novel relation extraction problem.
- Online Truth Discovery on Time Series Data31
This work proposes a novel online truth discovery framework that incorporates the predictions on the time series data into the truth estimation process and can improve the accuracy of the truth discovery results as well as the timeseries prediction.
- Influence-Aware Truth Discovery31
An unsupervised probabilistic model named IATD is proposed, which takes source correlations as prior for influence derivation and introduces "claim trustworthiness", which fuses thetrustworthiness of the source which provides the claim and the trustworthiness of its influencers.
- 30
- 30
- 30
- 29
- 29
- 28
- Contextualized Knowledge-aware Attentive Neural Network: Enhancing Answer Selection with Knowledge28
A context-knowledge interaction learning framework, Knowledge-aware Neural Network, which learns the QA sentence representations by considering a tight interaction with the external knowledge from KG and the textual information and develops two kinds of knowledge-aware attention mechanism to summarize both the context-based and knowledge-based interactions between questions and answers.
- 25
- 25
- 25
- 24
- 24
- 24
- 24
- 23
- 22
- 21
- 21
- Leveraging Long Short-Term User Preference in Conversational Recommendation via Multi-agent Reinforcement Learning20
This work proposes two novel multi-agent RL-based frameworks, namely Independent and Hierarchical Multi-Agent UNIfied COnversational RecommeNders (IMA-UNicORN and HMA-UNICORN), respectively, which significantly outperform state-of-the-art methods on the multi-round conversational recommendation.
- 18
- Bridging Hierarchical and Sequential Context Modeling for Question-driven Extractive Answer Summarization18
This paper designs a hierarchical compare-aggregate method to integrate the interaction between QA pairs in both word-level and sentence-level into the final question and answer representations and conducts the question-aware sequential extractor to produce a summary for the lengthy answer.
- 18
- 18
- 18
- 17
- 17
- 17
- 17
- 16
- 16
- 16
- 16
- 16
- MedTruth15
A new truth discovery method is proposed, MedTruth, for medical knowledge condition discovery, which incorporates prior source quality information into the source reliability estimation procedure, and also utilizes the knowledge triple information for trustworthy information computation.
- 14
- 14
- 14
- Transferability Bound Theory: Exploring Relationship between Adversarial Transferability and Flatness13
TPA is proposed, a Theoretically Provable Attack that optimizes a surrogate of the derived bound to craft adversarial examples that can craft more transferable adversarial examples compared to state-of-the-art baselines.
- 13
- 13
- 12
- 12
- 12
- 12
- 11
- 11
- 10
- 10
- 10
- 10
- 10
- 9
- 9
- 9
- 9
- 9
- 9
- Query-Oriented Keyphrase Extraction9
The empirical evaluation shows that using a named entity-based phraseness criterion and a language model-based informativeness score gives the best performance on the authors' task, and this method also outperforms two state-of-the-art baseline methods.
- 8
- 8
- 7
- 7
- 7
- 7
- 7
- Gastroenterology Ontology Construction Using Synonym Identification and Relation Extraction7
The proposed synonym identification and relation extraction method achieves the best performance compared with state-of-the-art methods and also builds a more complete ontology compared with existing gastroenterology disease ontologies.
- 6
- 6
- 6
- 6
- 6
- 6
- 6
- 6
- 6
- 5
- 5
- 5
- 5
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- When Truth Discovery Meets Medical Knowledge Graph: Estimating Trustworthiness Degree for Medical Knowledge Condition.4
A new truth discovery method is proposed to explore medical-related texts and infer trustworthiness degrees of knowledge triples associating with different conditions and demonstrates the effectiveness of the proposedtruth discovery method.
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 2
- 2
- 2
- 2
- 2
- 2
- Communication Efficient and Differentially Private Logistic Regression under the Distributed Setting2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-13. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.