Xiaolei Lu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Xiaolei Lu has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Tommy W. S. Chow
Department of Electrical Engineering, City University of Hong Kong, Hong Kong, SAR, China
5 shared publications - Haijun Zhang
Harbin Institute of Technology
2 shared publications - Jianghong Ma
Shenzhen Key Laboratory of Internet Information Collaboration, Shenzhen, China, Harbin Institute of Technology (Shenzhen), Shenzhen, China, and City University of Hong Kong, Shenzhen Research Institute, Shenzhen, China
2 shared publications - Jing Qiu
School of Mathematical Science, Qufu Normal University, Qufu, China
1 shared publication - Kangzhe Liu
School of Computer Science, Harbin Institute of Technology (Shenzhen), Shenzhen, China
1 shared publication - Rong Wang
School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China
1 shared publication
Latest Publications
- Open Access
Suboptimal Shapley Value Explanations
Deep Neural Networks (DNNs) have demonstrated strong capacity in supporting a wide variety of applications. Shapley value has emerged as a prominent tool to analyze feature importance to help people understand the inference process of deep neural models. Computing Shapley value function requires choosing a baseline to represent feature's missingness. However, existing random and conditional baselines could negatively influence the explanation. In this paper, by analyzing the suboptimality of different baselines, we identify the problematic baseline where the asymmetric interaction between $\bm{x}'_i$ (the replacement of the faithful influential feature) and other features has significant directional bias toward the model's output, and conclude that $p(y|\bm{x}'_i) = p(y)$ potentially minimizes the asymmetric interaction involving $\bm{x}'_i$. We further generalize the uninformativeness of $\bm{x}'_i$ toward the label space $L$ to avoid estimating $p(y)$ and design a simple uncertainty-based reweighting mechanism to accelerate the computation process. We conduct experiments on various NLP tasks and our quantitative analysis demonstrates the effectiveness of the proposed uncertainty-based reweighting mechanism. Furthermore, by measuring the consistency of explanations generated by explainable methods and human, we highlight the disparity between model inference and human understanding.Open AccessSuboptimal Shapley Value Explanations
Deep Neural Networks (DNNs) have demonstrated strong capacity in supporting a wide variety of applications. Shapley value has emerged as a prominent tool to analyze feature importance to help people understand the inference process of deep neural models. Computing Shapley value function requires choosing a baseline to represent feature's missingness. However, existing random and conditional baselines could negatively influence the explanation. In this paper, by analyzing the suboptimality of different baselines, we identify the problematic baseline where the asymmetric interaction between $\bm{x}'_i$ (the replacement of the faithful influential feature) and other features has significant directional bias toward the model's output, and conclude that $p(y|\bm{x}'_i) = p(y)$ potentially minimizes the asymmetric interaction involving $\bm{x}'_i$. We further generalize the uninformativeness of $\bm{x}'_i$ toward the label space $L$ to avoid estimating $p(y)$ and design a simple uncertainty-based reweighting mechanism to accelerate the computation process. We conduct experiments on various NLP tasks and our quantitative analysis demonstrates the effectiveness of the proposed uncertainty-based reweighting mechanism. Furthermore, by measuring the consistency of explanations generated by explainable methods and human, we highlight the disparity between model inference and human understanding. - 9 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Systems, Man, and Cybernetics: Systems
- Vol. 55 (4) , 2489-2502
Correlation-Driven Explainable Recommendation With Aspect and Rating Boosted Representation Learning: A Unified Joint-Ranking Framework
Recommender systems are essential in the ever-evolving landscape of e-commerce and social media platforms, delivering personalized recommendations by predicting user preferences. However, the growing need for explainable recommendation has arisen to enhance transparency and persuasiveness. In response, we present correlation-driven explainable recommendation with aspect and rating boosted representation learning (CER-ARRL), a unified joint-ranking framework that capitalizes on the robust capabilities of neural collaborative filtering to model the intricate dynamics among users, items, and explanations. By extracting information from explicit and implicit user emotional reviews, our framework enriches the representations of users and items. This integration yields simultaneous improvements in both item recommendation and explanation ranking tasks. In addition, CER-ARRL effectively exploits the structural correlation between phrases as well as the structural and semantic correlations between emojis to facilitate explanation ranking. This work represents the pioneering work to address the item-explanation joint recommendation task by integrating both interpretative phrases and illustrative emojis. Through extensive experiments on various datasets, including our collected dataset, we demonstrate the superiority of the proposed method over existing baselines.
- 9 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Systems, Man, and Cybernetics: Systems
- Vol. 55 (4) , 2489-2502
Correlation-Driven Explainable Recommendation With Aspect and Rating Boosted Representation Learning: A Unified Joint-Ranking Framework
Recommender systems are essential in the ever-evolving landscape of e-commerce and social media platforms, delivering personalized recommendations by predicting user preferences. However, the growing need for explainable recommendation has arisen to enhance transparency and persuasiveness. In response, we present correlation-driven explainable recommendation with aspect and rating boosted representation learning (CER-ARRL), a unified joint-ranking framework that capitalizes on the robust capabilities of neural collaborative filtering to model the intricate dynamics among users, items, and explanations. By extracting information from explicit and implicit user emotional reviews, our framework enriches the representations of users and items. This integration yields simultaneous improvements in both item recommendation and explanation ranking tasks. In addition, CER-ARRL effectively exploits the structural correlation between phrases as well as the structural and semantic correlations between emojis to facilitate explanation ranking. This work represents the pioneering work to address the item-explanation joint recommendation task by integrating both interpretative phrases and illustrative emojis. Through extensive experiments on various datasets, including our collected dataset, we demonstrate the superiority of the proposed method over existing baselines.
- Open Access
Does Faithfulness Conflict with Plausibility? An Empirical Study in Explainable AI across NLP Tasks
Explainability algorithms aimed at interpreting decision-making AI systems usually consider balancing two critical dimensions: 1) \textit{faithfulness}, where explanations accurately reflect the model's inference process. 2) \textit{plausibility}, where explanations are consistent with domain experts. However, the question arises: do faithfulness and plausibility inherently conflict? In this study, through a comprehensive quantitative comparison between the explanations from the selected explainability methods and expert-level interpretations across three NLP tasks: sentiment analysis, intent detection, and topic labeling, we demonstrate that traditional perturbation-based methods Shapley value and LIME could attain greater faithfulness and plausibility. Our findings suggest that rather than optimizing for one dimension at the expense of the other, we could seek to optimize explainability algorithms with dual objectives to achieve high levels of accuracy and user accessibility in their explanations.
Open AccessDoes Faithfulness Conflict with Plausibility? An Empirical Study in Explainable AI across NLP Tasks
Explainability algorithms aimed at interpreting decision-making AI systems usually consider balancing two critical dimensions: 1) \textit{faithfulness}, where explanations accurately reflect the model's inference process. 2) \textit{plausibility}, where explanations are consistent with domain experts. However, the question arises: do faithfulness and plausibility inherently conflict? In this study, through a comprehensive quantitative comparison between the explanations from the selected explainability methods and expert-level interpretations across three NLP tasks: sentiment analysis, intent detection, and topic labeling, we demonstrate that traditional perturbation-based methods Shapley value and LIME could attain greater faithfulness and plausibility. Our findings suggest that rather than optimizing for one dimension at the expense of the other, we could seek to optimize explainability algorithms with dual objectives to achieve high levels of accuracy and user accessibility in their explanations.
- 25 July 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 35 (2) , 2783-2792
Partial Sequence Labeling With Structured Gaussian Processes
Existing partial sequence labeling models mainly focus on a max-margin framework that fails to provide an uncertainty estimation of the prediction. Furthermore, the unique ground-truth disambiguation strategy employed by these models may include wrong label information for parameter learning. In this article, we propose structured Gaussian processes for partial sequence labeling (SGPPSL), which encodes uncertainty in the prediction and does not need extra effort for model selection and hyperparameter learning. The model employs factor-as-piece approximation that divides the linear-chain graph structure into the set of pieces, which preserves the basic Markov random field structure and effectively avoids handling a large number of candidate output sequences generated by partially annotated data. Then, confidence measure is introduced in the model to address different contributions of candidate labels, which enables the ground-truth label information to be utilized in parameter learning. Based on the derived lower bound of the variational lower bound of the proposed model, variational parameters and confidence measures are estimated in the framework of alternating optimization. Moreover, a weighted Viterbi algorithm is proposed to incorporate confidence measures to sequence prediction, which considers label ambiguity arose from multiple annotations in the training data and thus helps improve the performance. SGPPSL is evaluated on several sequence labeling tasks and the experimental results show the effectiveness of the proposed model.
- 25 July 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 35 (2) , 2783-2792
Partial Sequence Labeling With Structured Gaussian Processes
Existing partial sequence labeling models mainly focus on a max-margin framework that fails to provide an uncertainty estimation of the prediction. Furthermore, the unique ground-truth disambiguation strategy employed by these models may include wrong label information for parameter learning. In this article, we propose structured Gaussian processes for partial sequence labeling (SGPPSL), which encodes uncertainty in the prediction and does not need extra effort for model selection and hyperparameter learning. The model employs factor-as-piece approximation that divides the linear-chain graph structure into the set of pieces, which preserves the basic Markov random field structure and effectively avoids handling a large number of candidate output sequences generated by partially annotated data. Then, confidence measure is introduced in the model to address different contributions of candidate labels, which enables the ground-truth label information to be utilized in parameter learning. Based on the derived lower bound of the variational lower bound of the proposed model, variational parameters and confidence measures are estimated in the framework of alternating optimization. Moreover, a weighted Viterbi algorithm is proposed to incorporate confidence measures to sequence prediction, which considers label ambiguity arose from multiple annotations in the training data and thus helps improve the performance. SGPPSL is evaluated on several sequence labeling tasks and the experimental results show the effectiveness of the proposed model.
- 19 October 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cybernetics
- Vol. 53 (4) , 2335-2345
Modeling Sequential Annotations for Sequence Labeling With Crowds
Crowd sequential annotations can be an efficient and cost-effective way to build large datasets for sequence labeling. Different from tagging independent instances, for crowd sequential annotations, the quality of label sequence relies on the expertise level of annotators in capturing internal dependencies for each token in the sequence. In this article, we propose modeling sequential annotation for sequence labeling with crowds (SA-SLC). First, a conditional probabilistic model is developed to jointly model sequential data and annotators’ expertise, in which categorical distribution is introduced to estimate the reliability of each annotator in capturing local and nonlocal label dependencies for sequential annotation. To accelerate the marginalization of the proposed model, a valid label sequence inference (VLSE) method is proposed to derive the valid ground-truth label sequences from crowd sequential annotations. VLSE derives possible ground-truth labels from the tokenwise level and further prunes subpaths in the forward inference for label sequence decoding. VLSE reduces the number of candidate label sequences and improves the quality of possible ground-truth label sequences. The experimental results on several sequence labeling tasks of Natural Language Processing show the effectiveness of the proposed model.
- 19 October 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cybernetics
- Vol. 53 (4) , 2335-2345
Modeling Sequential Annotations for Sequence Labeling With Crowds
Crowd sequential annotations can be an efficient and cost-effective way to build large datasets for sequence labeling. Different from tagging independent instances, for crowd sequential annotations, the quality of label sequence relies on the expertise level of annotators in capturing internal dependencies for each token in the sequence. In this article, we propose modeling sequential annotation for sequence labeling with crowds (SA-SLC). First, a conditional probabilistic model is developed to jointly model sequential data and annotators’ expertise, in which categorical distribution is introduced to estimate the reliability of each annotator in capturing local and nonlocal label dependencies for sequential annotation. To accelerate the marginalization of the proposed model, a valid label sequence inference (VLSE) method is proposed to derive the valid ground-truth label sequences from crowd sequential annotations. VLSE derives possible ground-truth labels from the tokenwise level and further prunes subpaths in the forward inference for label sequence decoding. VLSE reduces the number of candidate label sequences and improves the quality of possible ground-truth label sequences. The experimental results on several sequence labeling tasks of Natural Language Processing show the effectiveness of the proposed model.
- Open Access
- 8 April 2021
- Published by Atlantis Press SARL
- p. 377-382
Research on the Relationship Between Online Learning Behavior and Learning Effect of College Students in the Digital Learning Environment
- 8 April 2021
- Published by Atlantis Press SARL
- p. 377-382
Open AccessResearch on the Relationship Between Online Learning Behavior and Learning Effect of College Students in the Digital Learning Environment
- 23 June 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cybernetics
- Vol. 52 (2) , 1258-1268
Weak Disambiguation for Partial Structured Output Learning
Existing disambiguation strategies for partial structured output learning just cannot generalize well to solve the problem that there are some candidates that can be false positive or similar to the ground-truth label. In this article, we propose a novel weak disambiguation for partial structured output learning (WD-PSL). First, a piecewise large margin formulation is generalized to partial structured output learning, which effectively avoids handling a large number of candidate-structured outputs for complex structures. Second, in the proposed weak disambiguation strategy, each candidate label is assigned with a confidence value indicating how likely it is the true label, which aims to reduce the negative effects of wrong ground-truth label assignment in the learning process. Then, two large margins are formulated to combine two types of constraints which are the disambiguation between candidates and noncandidates, and the weak disambiguation for candidates. In the framework of alternating optimization, a new 2n-slack variables cutting plane algorithm is developed to accelerate each iteration of optimization. The experimental results on several sequence labeling tasks of natural language processing show the effectiveness of the proposed model.
- 23 June 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cybernetics
- Vol. 52 (2) , 1258-1268
Weak Disambiguation for Partial Structured Output Learning
Existing disambiguation strategies for partial structured output learning just cannot generalize well to solve the problem that there are some candidates that can be false positive or similar to the ground-truth label. In this article, we propose a novel weak disambiguation for partial structured output learning (WD-PSL). First, a piecewise large margin formulation is generalized to partial structured output learning, which effectively avoids handling a large number of candidate-structured outputs for complex structures. Second, in the proposed weak disambiguation strategy, each candidate label is assigned with a confidence value indicating how likely it is the true label, which aims to reduce the negative effects of wrong ground-truth label assignment in the learning process. Then, two large margins are formulated to combine two types of constraints which are the disambiguation between candidates and noncandidates, and the weak disambiguation for candidates. In the framework of alternating optimization, a new 2n-slack variables cutting plane algorithm is developed to accelerate each iteration of optimization. The experimental results on several sequence labeling tasks of natural language processing show the effectiveness of the proposed model.
- 19 September 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 33 (4) , 1453-1466
Duration Modeling with Semi-Markov Conditional Random Fields for Keyphrase Extraction
Existing methods for keyphrase extraction need preprocessing to generate candidate phrase or post-processing to transform keyword into keyphrase. In this paper, we propose a novel approach called duration modeling with semi-Markov Conditional Random Fields (DM-SMCRFs) for keyphrase extraction. First of all, based on the property of semi-Markov chain, DM-SMCRFs can encode segment-level features and sequentially classify the phrase in the sentence as keyphrase or non-keyphrase. Second, by assuming the independence between state transition and state duration, DM-SMCRFs model the distribution of duration (length) of keyphrases to further explore state duration information, which can help identify the size of keyphrase. Based on the convexity of parametric duration feature derived from duration distribution, a constrained Viterbi algorithm is derived to improve the performance of decoding in DM-SMCRFs. We thoroughly evaluate the performance of DM-SMCRFs on the datasets from various domains. The experimental results demonstrate the effectiveness of proposed model.
- 19 September 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 33 (4) , 1453-1466
Duration Modeling with Semi-Markov Conditional Random Fields for Keyphrase Extraction
Existing methods for keyphrase extraction need preprocessing to generate candidate phrase or post-processing to transform keyword into keyphrase. In this paper, we propose a novel approach called duration modeling with semi-Markov Conditional Random Fields (DM-SMCRFs) for keyphrase extraction. First of all, based on the property of semi-Markov chain, DM-SMCRFs can encode segment-level features and sequentially classify the phrase in the sentence as keyphrase or non-keyphrase. Second, by assuming the independence between state transition and state duration, DM-SMCRFs model the distribution of duration (length) of keyphrases to further explore state duration information, which can help identify the size of keyphrase. Based on the convexity of parametric duration feature derived from duration distribution, a constrained Viterbi algorithm is derived to improve the performance of decoding in DM-SMCRFs. We thoroughly evaluate the performance of DM-SMCRFs on the datasets from various domains. The experimental results demonstrate the effectiveness of proposed model.
- 1 July 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 1483-1487
Piecewise Large Margin Learning for Partially Annotated Sequences
Supervised and semi-supervised sequence labeling methods require large amounts of fully annotated training sequences or exact annotations of structured outputs. The problem of learning from partially annotated sequences arises in many applications, for example, Natural Language Processing and Computational Biology. In this paper, we propose Piecewise Convex Learning from Partial Labels (PW-CLPL) which is an effective discriminative structured learning method for sequence labeling as global training is intractable for partially annotated sequences. A small number of constraints is reformulated for the optimization, which improve the efficiency of parameters learning. Experimental results on the reconstructed dataset CoNLL-2000 show the effectiveness of the proposed model in the setting of partial annotations.
- 1 July 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 1483-1487
Piecewise Large Margin Learning for Partially Annotated Sequences
Supervised and semi-supervised sequence labeling methods require large amounts of fully annotated training sequences or exact annotations of structured outputs. The problem of learning from partially annotated sequences arises in many applications, for example, Natural Language Processing and Computational Biology. In this paper, we propose Piecewise Convex Learning from Partial Labels (PW-CLPL) which is an effective discriminative structured learning method for sequence labeling as global training is intractable for partially annotated sequences. A small number of constraints is reformulated for the optimization, which improve the efficiency of parameters learning. Experimental results on the reconstructed dataset CoNLL-2000 show the effectiveness of the proposed model in the setting of partial annotations.