Author name cluster

Xingyi Zhang

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

23 papers

1 author row

AAAI Conference 2026 Conference Paper

Debiased Cognitive Diagnosis: A Contrastive Counterfactual Modeling Method via Variational Autoencoder

Shangshang Yang
Xuewen Duan
Xiaoshan Yu
Ziwen Wang
Haiping Ma
Xingyi Zhang

Cognitive diagnosis (CD), inferring student knowledge mastery based on historical response records, is crucial for personalized educational services such as adaptive practice and learning path planning. Existing CD models were built based on the assumption that student's response data is integral, overlooking the nonrandom missingness of data caused by student answering exercises selectively. This missingness generally leads to biased and incomplete observations, where confounders, such as selection bias and exposure bias, significantly undermine the accuracy of student knowledge modeling. To address missingness, we propose a Debiased Cognitive Diagnosis (DBCD) framework through the perspective of counterfactual modeling to remove exogenous confounders from the response data. Specifically, the proposed DBCD achieves debiasing for CD by applying the idea of contrastive learning to constrain the model's prediction distributions on both factual and counterfactual data. For a student, the factual data is his/her original response records, while the counterfactual data is generated by sampling the same number of exercises from all exercises of each concept through a similarity-based counterfactual sampling strategy. Considering the difficulty of directly removing the exogenous confounders for student, we devise a β-Variational Autoencoder to model their exogenous confounders within the latent representations of knowledge proficiency by leveraging exercise priors and student response patterns. Then, the learned representations are further combined with the vanilla student's ability embedding via a gating mechanism-based fusion for final diagnosis prediction of the model. Extensive experiments on real-world educational datasets demonstrate that the proposed DBCD effectively mitigates confounders and even outperforms existing methods, thereby validating the feasibility and effectiveness of the DBCD framework.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Multimodal Mixture-of-Experts with Retrieval Augmentation for Protein Active Site Identification

Jiayang Wu
Jiale Zhou
Rubo Wang
Xingyi Zhang
Xun Lin
Tianxu Lv
Leong Hou U
Yefeng Zheng

Accurate identification of protein active sites at the residue level is crucial for understanding protein function and advancing drug discovery. However, current methods face two critical challenges: vulnerability in single-instance prediction due to sparse training data, and inadequate modality reliability estimation that leads to performance degradation when unreliable modalities dominate fusion processes. To address these challenges, we introduce Multimodal Mixtureof-Experts with Retrieval Augmentation (MERA), the first retrieval-augmented framework for protein active site identification. MERA employs hierarchical multi-expert retrieval that dynamically aggregates contextual information from chain, sequence, and active-site perspectives through residuelevel mixture-of-experts gating. To prevent modality degradation, we propose a reliability-aware fusion strategy based on Dempster–Shafer evidence theory that quantifies modality trustworthiness through belief mass functions and learnable discounting coefficients, enabling principled multimodal integration. Extensive experiments on ProTAD-Gen and TS125 datasets demonstrate that MERA achieves state-of-the-art performance, with 90% AUPRC on active site prediction and significant gains on peptide-binding site identification, validating the effectiveness of retrieval-augmented multi-expert modeling and reliability-guided fusion

PDF Details DOI

AAAI Conference 2026 Conference Paper

PEOAT: Personalization-Guided Evolutionary Question Assembly for One-Shot Adaptive Testing

Xiaoshan Yu
Ziwei Huang
Shangshang Yang
Ziwen Wang
Haiping Ma
Xingyi Zhang

With the rapid advancement of intelligent education, Computerized Adaptive Testing (CAT) has attracted increasing attention by integrating educational psychology with deep learning technologies. Unlike traditional paper-and-pencil testing, CAT aims to efficiently and accurately assess ex- aminee abilities by adaptively selecting the most suitable items during the assessment process. However, its real-time and sequential nature presents limitations in practical scenarios, particularly in large-scale assessments where interaction costs are high, or in sensitive domains such as psychological evaluations where minimizing noise and interfer- ence is essential. These challenges constrain the applicability of conventional CAT methods in time-sensitive or resource- constrained environments. To this end, we first introduce a novel task called one-shot adaptive testing (OAT), which aims to select a fixed set of optimal items for each test-taker in a one-time selection. Meanwhile, we propose PEOAT, a Personalization-guided Evolutionary question assembly framework for One-hot Adaptive Testing from the perspec- tive of combinatorial optimization. Specifically, we began by designing a personalization-aware initialization strategy that integrates differences between examinee ability and ex- ercise difficulty, using multi-strategy sampling to construct a diverse and informative initial population. Building on this, we proposed a cognitive-enhanced evolutionary framework incorporating schema-preserving crossover and cognitively guided mutation to enable efficient exploration through infor- mative signals. To maintain diversity without compromising fitness, we further introduced a diversity-aware environmen- tal selection mechanism. The effectiveness of PEOAT is val- idated through extensive experiments on two datasets, com- plemented by case studies that uncovered valuable insights.

PDF Details DOI

TIST Journal 2026 Journal Article

Personalized Forgetting Mechanism with Concept-Driven Knowledge Tracing

Shanshan Wang
Ying Hu
Qianru Li
Xun Yang
Zhongzhou Zhang
Keyang Wang
Xingyi Zhang

Knowledge Tracing (KT) aims to trace changes in students’ knowledge states throughout their entire learning process by analyzing their historical learning data and predicting their future learning performance. Existing forgetting curve theory based knowledge tracing models only consider the general forgetting caused by time intervals, ignoring the specific influences in KT task. Firstly, the discriminative information in forgetting curve is personalized due to the difference of students. Secondly, the relationship between knowledge concepts could contribute to the generalized features in the forgetting process. Considering these two aspects, we propose a C oncept-driven P ersonalized F orgetting knowledge tracing model (CPF) which integrates the relationships between knowledge concepts and the personalization of students in cognitive abilities. First, personalized cognitive abilities are integrated into the learning and forgetting processes. Individual cognitive differences are modeled to dynamically adjust learning gains and forgetting rates based on students’ knowledge mastery and learning strategies, which enables a more personalized learning experience. Second, the hierarchical relationships among knowledge concepts are considered by designing a precursor-successor knowledge concept matrix. In this way, the potential impact of forgetting prior knowledge concepts on subsequent ones is also integrated in KT task. Furthermore, the proposed personalized forgetting mechanism not only could be applied into the learning of specific knowledge concepts but also in the forgetting-review mechanism of life-long learning process. Extensive experimental results on several public datasets show that our CPF outperforms current forgetting curve theory based methods in predicting student performance, demonstrating CPF can better simulate changes in students’ knowledge state through the personalized forgetting mechanism. Our code is publicly available at https://github.com/lqr-1169/CPF.

Details DOI

AAAI Conference 2026 Conference Paper

QuEPT: Quantized Elastic Precision Transformers with One-Shot Calibration for Multi-Bit Switching

Ke Xu
Yixin Wang
Zhongcheng Li
Hao Cui
Jinshui Hu
Xingyi Zhang

Elastic precision quantization enables multi-bit deployment via a single optimization pass, fitting diverse quantization scenarios. Yet, the high storage and optimization costs associated with the Transformer architecture, research on elastic quantization remains limited, particularly for large language models. This paper proposes QuEPT, an efficient post-training scheme that reconstructs block-wise multi-bit errors with one-shot calibration on a small data slice. It can dynamically adapt to various predefined bit-widths by cascading different low-rank adapters, and supports real-time switching between uniform quantization and mixed precision quantization without repeated optimization. To enhance accuracy and robustness, we introduce Multi-Bit Token Merging (MB-ToMe) to dynamically fuse token features across different bit-widths, improving robustness during bit-width switching. Additionally, we propose Multi-Bit Cascaded Low-Rank adapters (MB-CLoRA) to strengthen correlations between bit-width groups, further improve the overall performance of QuEPT. Extensive experiments demonstrate that QuEPT achieves comparable or better performance to existing state-of-the-art post-training quantization methods.

PDF Details DOI

TIST Journal 2026 Journal Article

Reconciling Cognitive Modeling with Knowledge Forgetting: A Continuous Time-aware General Neural Network Framework

Ziwen Wang
Jingyuan Wang
Haiping Ma
Hengshu Zhu
Shangshang Yang
Xiaoshan Yu
Shuhuan Liu
Haifeng Zhang

Cognitive modeling, as an emerging technology in the field of computer-aided education, aims to explore students’ knowledge levels and learning abilities to achieve various intelligent educational applications. Although some existing work focuses on addressing the problem of student forgetting, it is still a less explored area how to naturally integrate the forgetting effect caused by the time interval between answering exercises into student knowledge state modeling. Additionally, traditional cognitive modeling methods mostly assume that students answer exercises one by one, which often does not align with real answering behavior and cannot be directly extended to diverse learning scenarios. Therefore, in this article, we propose a Continuous Time-based Neural Cognitive (CT-NC) framework and several implemented models (CT-NCM and two extensions) to effectively integrate the dynamic and continuous characteristics of knowledge forgetting into student learning process modeling, making it more natural. Specifically, we adopt a specially designed learning event encoding method to adjust the neural Hawkes process to capture the relationship between knowledge learning and forgetting over continuous time. Furthermore, we propose a customizable learning function to jointly model the changes in different knowledge states and their interaction with each practice moment. In the end, we demonstrate an extension CT-NCM+ that can adapt well to diverse learning scenarios, indicating that CT-NCM can solve real-world problems by flexibly adjusting its structure. Extensive experimental results on real datasets clearly demonstrate that CT-NCM and CT-NCM+ outperform the current state-of-the-art KT methods in student performance prediction, while our work points out a realistic research direction for KT and demonstrates its interpretability in knowledge learning visualization.

Details DOI

AAAI Conference 2026 Conference Paper

UniABG: Unified Adversarial View Bridging and Graph Correspondence for Unsupervised Cross-View Geo-Localization

Cuiqun Chen
Qi Chen
Bin Yang
Xingyi Zhang

Cross-view geo-localization (CVGL) matches query images (e.g., drone) to geographically corresponding opposite-view imagery (e.g., satellite). While supervised methods achieve strong performance, their reliance on extensive pairwise annotations limits scalability. Unsupervised alternatives avoid annotation costs but suffer from noisy pseudo-labels due to intrinsic cross-view domain gaps. To address these limitations, we propose UniABG, a novel dual-stage unsupervised cross-view geo-localization framework integrating adversarial view bridging with graph-based correspondence calibration. Our approach first employs View-Aware Adversarial Bridging (VAAB) to model view-invariant features and enhance pseudo-label robustness. Subsequently, Heterogeneous Graph Filtering Calibration (HGFC) refines cross-view associations by constructing dual inter-view structure graphs, achieving reliable view correspondence. Extensive experiments demonstrate state-of-the-art unsupervised performance, showing that UniABG improves Satellite → Drone AP by +10.63% on University-1652 and +16.73% on SUES-200, even surpassing supervised baselines.

PDF Details DOI

AAAI Conference 2025 Conference Paper

Explicit and Implicit Examinee-Question Relation Exploiting for Efficient Computerized Adaptive Testing

Changqian Wang
Shangshang Yang
Siyu Song
Ziwen Wang
Haiping Ma
Xingyi Zhang
Bo Jin

Computerized adaptive testing(CAT) is a crucial task in computer-aided education, which aims to adaptively select suitable question to diagnose examinees' ability status. Existing CAT approaches enhance selection performance by exploring examinee-question(E-Q) relation. These approaches either exclusively utilize explicit E-Q relation. For instance, policy-based approaches determine question selection based on predefined criteria. While effective in adapting to changes in question banks, these methods often entail significant computational costs in searching for suitable questions. Conversely, some studies focus solely on implicit E-Q relation. For example, learning-based approaches train agents to efficiently select questions by learning from large-scale datasets. However, they may struggle with newly introduced questions. Additionally, most of these existing question selectors are based on greedy strategies, which potentially overlooks promising quuestions. To bridge the above two types of approaches, we propose a novel framework named Relation Exploiting-based CAT(RECAT) by exploring and exploiting the implicit and explicit examinee-question relation. Specifically, we first define an examinee true ability-oriented selection objective to select more suitable questions. Then, to learn the implicit E-Q relation, we design a question selector, which explores the examinee ability and generates best-fitting questions for specific examinee ability from two aspects, including generation consistency and knowledge matching. The former aims to maximize the likelihood estimation of the implicit E-Q relation learning process, while the latter is employed to fit the distribution of real questions. To fully exploit explicit E-Q relation, we generate a high-quality candidate set for the given examinee's ability using implicit E-Q relation, which streamlines the search process, minimizing selection latency. We demonstrate the effectiveness and efficiency of our framework through comprehensive experiments on real-world datasets.

PDF Details DOI

EAAI Journal 2025 Journal Article

Varied granularity encoding based evolutionary algorithm for multi-objective intensity-modulated radiation therapy optimization

Langchun Si
Xingyi Zhang
Ye Tian
Ruifen Cao
Shangshang Yang
Limiao Zhang

Intensity-modulated radiation therapy is an interesting multi-objective optimization problem, which holds a large number of aperture shape-related variables, posing a stiff challenge to existing algorithms. To efficiently solve this problem, we propose a varied granularity encoding method in this paper, where the granularity of encoding of the shape in the multi-leaf collimator is progressively refined during the optimization. Specifically, at the beginning of the search, a coarse encoding is adopted by dividing the aperture shape-related variables into several groups and representing each group by one bit, which achieves effective search space reduction for the aperture shape. During the evolution, the granularity of encoding aperture shape-related variables is gradually varied from coarse to fine by reducing the size of each group until only one variable is contained in the group. With the proposed varied granularity encoding method, an evolutionary algorithm is suggested based on a popular evolutionary multi-objective framework (NSGA-II), where an adaptive switching method is developed to determine whether the granularity level needs to be reduced according to the convergence status of the population. The experiment empirically investigates the performance of the proposed varied granularity encoding method based evolutionary algorithm on eight clinical instances with the number of aperture shape-related variables ranging from 1932 to 3180. Compared with seven representative evolutionary algorithms and one traditional direct aperture optimization algorithm, the proposed algorithm demonstrates statistically significant improvements in hypervolume, inverted generational distance, and dose-volume histogram. The experimental results reveal that the proposed algorithm not only exhibits competitiveness but reduces computational time in radiotherapy optimization.

Details DOI

EAAI Journal 2024 Journal Article

A co-evolutionary algorithm based on sparsity clustering for sparse large-scale multi-objective optimization

Yajie Zhang
Chengming Wu
Ye Tian
Xingyi Zhang

Sparse large-scale multi-objective optimization problems (LSMOPs), which are characterized by high dimensional search space and sparse Pareto optimal solutions, have a widespread existence in academic research and practical applications. While the high dimensional decision space poses challenges to multi-objective evolutionary algorithms (MOEAs), the difficulty of solving sparse LSMOPs can be alleviated by utilizing the prior knowledge that the optimal solutions are sparse. In this paper, a co-evolutionary algorithm based on sparsity clustering, namely SCEA, is proposed, where the prior knowledge of sparse optimal solutions is utilized explicitly. At each generation, SCEA first calculates the current optimal sparsity by sparsity clustering. Then, SCEA divides the population into a winner subpopulation and two loser subpopulations. While the winner subpopulation reproduces offspring solutions by conventional genetic operators, the loser subpopulations generate offspring solutions along two competitive directions under the guidance of current optimal sparsity and variable importance. In the experiments, four state-of-the-art MOEAs are selected as the comparative algorithms. Experimental results show that the proposed algorithm is superior to the four competitors on both benchmark problems and practical applications, which include the sparse signal reconstruction problem, the community detection problem, and the instance selection problem.

Details DOI

EAAI Journal 2024 Journal Article

A robustness division based multi-population evolutionary algorithm for solving vehicle routing problems with uncertain demand

Hao Jiang
Yanhui Tong
Bowen Song
Chao Wang
Jiahang Li
Qi Liu
Xingyi Zhang

The vehicle routing problem with uncertain demand (VRPUD) is an extension of capacitated vehicle routing problem (CVRP), where the demand of each customer is unknown when dispatching the vehicles to service customers. Since it is more practical than CVRP, the VRPUD has aroused wide attention. Although the evolutionary algorithms (EAs) have demonstrate its promising performance on solving VRPUD, the most of EAs only consider the robustness of solution after generating offspring, which limit the quality of solutions found by EAs. To this end, in this paper, a robustness division based multi-population evolutionary algorithm (RDMPEA) is developed for VRPUDs, where the robustness is considered before, during and after offspring. Specifically, before generating offspring, the RDMPEA first divides the individuals into different subpopulations according to their robustness level, and only the individuals within the same subpopulation can match each other and generate offspring. During generating offspring, the RDMPEA employs a route based crossover operator to generate offspring, where the routes with higher robustness have a greater probability of being inherited by the offspring. After generating offspring, a dedicated environment selection strategy is applied to survive the individuals with better robustness and travel cost. In the experiments, the proposed RDMPEA is compared to three state-of-the-art heuristic methods tailored for VRPUDs on a variety of instances obtained by using three widely used vehicle routing problem benchmarks. The experimental results indicate that the proposed RDMPEA is superior to three compared algorithms, and can find solutions with better travel cost and robustness.

Details DOI

AAAI Conference 2024 Conference Paper

Boosting Neural Cognitive Diagnosis with Student’s Affective State Modeling

Shanshan Wang
Zhen Zeng
Xun Yang
Ke Xu
Xingyi Zhang

Cognitive Diagnosis Modeling aims to infer students' proficiency level on knowledge concepts from their response logs. Existing methods typically model students’ response processes as the interaction between students and exercises or concepts based on hand-crafted or deeply-learned interaction functions. Despite their promising achievements, they fail to consider the relationship between students' cognitive states and affective states in learning, e.g., the feelings of frustration, boredom, or confusion with the learning content, which is insufficient for comprehensive cognitive diagnosis in intelligent education. To fill the research gap, we propose a novel Affect-aware Cognitive Diagnosis (ACD) model which can effectively diagnose the knowledge proficiency levels of students by taking into consideration the affective factors. Specifically, we first design a student affect perception module under the assumption that the affective state is jointly influenced by the student's affect trait and the difficulty of the exercise. Then, our inferred affective distribution is further used to estimate the student's subjective factors, i.e., guessing and slipping, respectively. Finally, we integrate the estimated guessing and slipping parameters with the basic neural cognitive diagnosis framework based on the DINA model, which facilitates the modeling of complex exercising interactions in a more accurate and interpretable fashion. Besides, we also extend our affect perception module in an unsupervised learning setting based on contrastive learning, thus significantly improving the compatibility of our ACD. To the best of our knowledge, we are the first to unify the cognition modeling and affect modeling into the same framework for student cognitive diagnosis. Extensive experiments on real-world datasets clearly demonstrate the effectiveness of our ACD. Our code is available at https://github.com/zeng-zhen/ACD.

PDF Details DOI

IJCAI Conference 2024 Conference Paper

DGCD: An Adaptive Denoising GNN for Group-level Cognitive Diagnosis

Haiping Ma
Siyu Song
Chuan Qin
Xiaoshan Yu
Limiao Zhang
Xingyi Zhang
Hengshu Zhu

Group-level cognitive diagnosis, pivotal in intelligent education, aims to effectively assess group-level knowledge proficiency by modeling the learning behaviors of individuals within the group. Existing methods typically conceptualize the group as an abstract entity or aggregate the knowledge levels of all members to represent the group’s overall ability. However, these methods neglect the high-order connectivity among groups, students, and exercises within the context of group learning activities, along with the noise present in their interactions, resulting in less robust and suboptimal diagnosis performance. To this end, in this paper, we propose DGCD, an adaptive Denoising graph neural network for realizing effective Group-level Cognitive Diagnosis. Specifically, we first construct a group-student-exercise (GSE) graph to explicitly model higher-order connectivity among groups, students, and exercises, contributing to the acquisition of informative representations. Then, we carefully design an adaptive denoising module, integrated into the graph neural network, to model the reliability distribution of student-exercise edges for mining purer interaction features. In particular, edges of lower reliability are more prone to exclusion, thereby reducing the impact of noisy interactions. Furthermore, recognizing the relational imbalance in the GSE graph, which could potentially introduce bias during message passing, we propose an entropy-weighted balance module to mitigate such bias. Finally, extensive experiments conducted on four real-world educational datasets clearly demonstrate the effectiveness of our proposed DGCD model. The code is available at https: //github. com/BIMK/Intelligent-Education/tree/main/DGCD.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

DisenGCD: A Meta Multigraph-assisted Disentangled Graph Learning Framework for Cognitive Diagnosis

Shangshang Yang
Mingyang Chen
Ziwen Wang
Xiaoshan Yu
Panpan Zhang
Haiping Ma
Xingyi Zhang

Existing graph learning-based cognitive diagnosis (CD) methods have made relatively good results, but their student, exercise, and concept representations are learned and exchanged in an implicit unified graph, which makes the interaction-agnostic exercise and concept representations be learned poorly, failing to provide high robustness against noise in students' interactions. Besides, lower-order exercise latent representations obtained in shallow layers are not well explored when learning the student representation. To tackle the issues, this paper suggests a meta multigraph-assisted disentangled graph learning framework for CD (DisenGCD), which learns three types of representations on three disentangled graphs: student-exercise-concept interaction, exercise-concept relation, and concept dependency graphs, respectively. Specifically, the latter two graphs are first disentangled from the interaction graph. Then, the student representation is learned from the interaction graph by a devised meta multigraph learning module; multiple learnable propagation paths in this module enable current student latent representation to access lower-order exercise latent representations, which can lead to more effective nad robust student representations learned; the exercise and concept representations are learned on the relation and dependency graphs by graph attention modules. Finally, a novel diagnostic function is devised to handle three disentangled representations for prediction. Experiments show better performance and robustness of DisenGCD than state-of-the-art CD methods and demonstrate the effectiveness of the disentangled learning framework and meta multigraph module. The source code is available at https: //github. com/BIMK/Intelligent-Education/tree/main/DisenGCD.

PDF Details DOI

AAAI Conference 2024 Conference Paper

Enhancing Cognitive Diagnosis Using Un-interacted Exercises: A Collaboration-Aware Mixed Sampling Approach

Haiping Ma
Changqian Wang
Hengshu Zhu
Shangshang Yang
Xiaoming Zhang
Xingyi Zhang

Cognitive diagnosis is a crucial task in computer-aided education, aimed at evaluating students' proficiency levels across various knowledge concepts through exercises. Current models, however, primarily rely on students' answered exercises, neglecting the complex and rich information contained in un-interacted exercises. While recent research has attempted to leverage the data within un-interacted exercises linked to interacted knowledge concepts, aiming to address the long-tail issue, these studies fail to fully explore the informative, un-interacted exercises related to broader knowledge concepts. This oversight results in diminished performance when these models are applied to comprehensive datasets. In response to this gap, we present the Collaborative-aware Mixed Exercise Sampling (CMES) framework, which can effectively exploit the information present in un-interacted exercises linked to un-interacted knowledge concepts. Specifically, we introduce a novel universal sampling module where the training samples comprise not merely raw data slices, but enhanced samples generated by combining weight-enhanced attention mixture techniques. Given the necessity of real response labels in cognitive diagnosis, we also propose a ranking-based pseudo feedback module to regulate students' responses on generated exercises. The versatility of the CMES framework bolsters existing models and improves their adaptability. Finally, we demonstrate the effectiveness and interpretability of our framework through comprehensive experiments on real-world datasets.

PDF Details DOI

AAAI Conference 2024 Conference Paper

PTMQ: Post-training Multi-Bit Quantization of Neural Networks

Ke Xu
Zhongcheng Li
Shanshan Wang
Xingyi Zhang

The ability of model quantization with arbitrary bit-width to dynamically meet diverse bit-width requirements during runtime has attracted significant attention. Recent research has focused on optimizing large-scale training methods to achieve robust bit-width adaptation, which is a time-consuming process requiring hundreds of GPU hours. Furthermore, converting bit-widths requires recalculating statistical parameters of the norm layers, thereby impeding real-time switching of the bit-width. To overcome these challenges, we propose an efficient Post-Training Multi-bit Quantization (PTMQ) scheme that requires only a small amount of calibration data to perform block-wise reconstruction of multi-bit quantization errors. It eliminates the influence of statistical parameters by fusing norm layers, and supports real-time switching bit-widths in uniform quantization and mixed-precision quantization. To improve quantization accuracy and robustness, we propose a Multi-bit Feature Mixer technique (MFM) for fusing features of different bit-widths to enhance robustness across varying bit-widths. Moreover, we introduced the Group-wise Distillation Loss (GD-Loss) to enhance the correlation between different bit-width groups and further improve the overall performance of PTMQ. Extensive experiments demonstrate that PTMQ achieves comparable performance to existing state-of-the-art post-training quantization methods, while optimizing it speeds up by 100$\times$ compared to recent multi-bit quantization works. Code can be available at https://github.com/xuke225/PTMQ.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

Evolutionary Neural Architecture Search for Transformer in Knowledge Tracing

Shangshang Yang
Xiaoshan Yu
Ye Tian
Xueming Yan
Haiping Ma
Xingyi Zhang

Knowledge tracing (KT) aims to trace students' knowledge states by predicting whether students answer correctly on exercises. Despite the excellent performance of existing Transformer-based KT approaches, they are criticized for the manually selected input features for fusion and the defect of single global context modelling to directly capture students' forgetting behavior in KT, when the related records are distant from the current record in terms of time. To address the issues, this paper first considers adding convolution operations to the Transformer to enhance its local context modelling ability used for students' forgetting behavior, then proposes an evolutionary neural architecture search approach to automate the input feature selection and automatically determine where to apply which operation for achieving the balancing of the local/global context modelling. In the search space, the original global path containing the attention module in Transformer is replaced with the sum of a global path and a local path that could contain different convolutions, and the selection of input features is also considered. To search the best architecture, we employ an effective evolutionary algorithm to explore the search space and also suggest a search space reduction strategy to accelerate the convergence of the algorithm. Experimental results on the two largest and most challenging education datasets demonstrate the effectiveness of the architecture found by the proposed approach.

PDF Details

AAAI Conference 2023 Conference Paper

Self-Supervised Graph Learning for Long-Tailed Cognitive Diagnosis

Shanshan Wang
Zhen Zeng
Xun Yang
Xingyi Zhang

Cognitive diagnosis is a fundamental yet critical research task in the field of intelligent education, which aims to discover the proficiency level of different students on specific knowledge concepts. Despite the effectiveness of existing efforts, previous methods always considered the mastery level on the whole students, so they still suffer from the Long Tail Effect. A large number of students who have sparse interaction records are usually wrongly diagnosed during inference. To relieve the situation, we proposed a Self-supervised Cognitive Diagnosis (SCD) framework which leverages the self-supervised manner to assist the graph-based cognitive diagnosis, then the performance on those students with sparse data can be improved. Specifically, we came up with a graph confusion method that drops edges under some special rules to generate different sparse views of the graph. By maximizing the cross-view consistency of node representations, our model could pay more attention on long-tailed students. Additionally, we proposed an importance-based view generation rule to improve the influence of long-tailed students. Extensive experiments on real-world datasets show the effectiveness of our approach, especially on the students with much sparser interaction records. Our code is available at https://github.com/zeng-zhen/SCD.

PDF Details DOI

IJCAI Conference 2022 Conference Paper

MultiQuant: Training Once for Multi-bit Quantization of Neural Networks

Ke Xu
Qiantai Feng
Xingyi Zhang
Dong Wang

Quantization has become a popular technique to compress deep neural networks (DNNs) and reduce computational costs, but most prior work focuses on training DNNs at each individual fixed bit-width and accuracy trade-off point. How to produce a model with flexible precision is largely unexplored. This work proposes a multi-bit quantization framework (MultiQuant) to make the learned DNNs robust for different precision configuration during inference by adopting Lowest-Random-Highest bit-width co-training method. Meanwhile, we propose an online adaptive label generation strategy to alleviate the problem of vicious competition under different precision caused by one-hot labels in the supernet training. The trained supernet model can be flexibly set to different bit widths to support dynamic speed and accuracy trade-off. Furthermore, we adopt the Monte Carlo sampling-based genetic algorithm search strategy with quantization-aware accuracy predictor as evaluation criterion to incorporate the mixed precision technology in our framework. Experiment results on ImageNet datasets demonstrate MultiQuant method can attain the quantization results under different bit-widths comparable with quantization-aware training without retraining.

PDF Details DOI

IJCAI Conference 2022 Conference Paper

Reconciling Cognitive Modeling with Knowledge Forgetting: A Continuous Time-aware Neural Network Approach

Haiping Ma
Jingyuan Wang
Hengshu Zhu
Xin Xia
Haifeng Zhang
Xingyi Zhang
Lei Zhang

As an emerging technology of computer-aided education, cognitive modeling aims at discovering the knowledge proficiency or learning ability of students, which can enable a wide range of intelligent educational applications. While considerable efforts have been made in this direction, a long-standing research challenge is how to naturally integrate the forgetting mechanism into the learning process of knowledge concepts. To this end, in this paper, we propose a novel Continuous Time based Neural Cognitive Modeling(CT-NCM) approach to integrate the dynamism and continuity of knowledge forgetting into students' learning process modeling in a realistic manner. To be specific, we first adapt the neural Hawkes process with a specially-designed learning event encoding method to model the relationship between knowledge learning and forgetting with continuous time. Then, we propose a learning function with extendable settings to jointly model the change of different knowledge states and their interactions with the exercises at each moment. In this way, CT-NCM can simultaneously predict the future knowledge state and exercise performance of students. Finally, we conduct extensive experiments on five real-world datasets with various benchmark methods. The experimental results clearly validate the effectiveness of CT-NCM and show its interpretability in terms of knowledge learning visualization.

PDF Details DOI

EAAI Journal 2020 Journal Article

Demand coverage diversity based ant colony optimization for dynamic vehicle routing problems

Xiaoshu Xiang
Jianfeng Qiu
Jianhua Xiao
Xingyi Zhang

Dynamic vehicle routing problem (DVRP) has attracted increasing attention due to its wide applications in logistics. Compared with the static vehicle routing problem, DVRP is characterized by the prior unknown customer requests dynamically appearing in route execution. Nevertheless, the newly appeared customers pose a great challenge to route optimizer, since the optimized route may be contrarily of bad quality when including the new customers that are far from planned routes in route planning. To address this issue, in this paper we propose a demand coverage diversity based metaheuristic, termed ACO-CD, in the framework of ant colony algorithm. In ACO-CD, a demand coverage diversity adaptation method is suggested to maintain the diversity of covered customers in routes so that the optimizer can effectively response to the newly appeared customer requests. Experimental results on 27 DVRP test instances demonstrate the effectiveness of the proposed demand coverage diversity adaptation method and the superiority of the proposed ACO-CD over four state-of-the-art DVRP algorithms in terms of solution quality.

Details DOI

TCS Journal 2010 Journal Article

Deterministic solutions to QSAT and Q3SAT by spiking neural P systems with pre-computed resources

Tseren-Onolt Ishdorj
Alberto Leporati
Linqiang Pan
Xiangxiang Zeng
Xingyi Zhang

In this paper we continue previous studies on the computational efficiency of spiking neural P systems, under the assumption that some pre-computed resources of exponential size are given in advance. Specifically, we give a deterministic solution for each of two well known PSPACE-complete problems: QSAT and Q3SAT. In the case of QSAT, the answer to any instance of the problem is computed in a time which is linear with respect to both the number n of Boolean variables and the number m of clauses that compose the instance. As for Q3SAT, the answer is computed in a time which is at most cubic in the number n of Boolean variables.

Details DOI

TCS Journal 2009 Journal Article

On languages generated by asynchronous spiking neural P systems

Xingyi Zhang
Xiangxiang Zeng
Linqiang Pan

In this paper, we investigate the languages generated by asynchronous spiking neural P systems. Characterizations of finite languages and recursively enumerable languages are obtained by asynchronous spiking neural P systems with extended rules. The relationships of the languages generated by asynchronous spiking neural P systems with regular and non-semilinear languages are also investigated.

Details DOI