Epicardial adipose tissue (EAT) is increasingly recognized as an important contributor to cardiovascular disease (CVD), but its spatial distribution across the heart remains insufficiently characterized due to limitations in existing segmentation and analysis methods. In this study, we developed a deep learning-based framework that integrates automated cardiac MRI segmentation with spatial statistical modeling to enable quantitative, chamber-resolved characterization of EAT distribution. An asymmetric multi-modal CNN-Transformer network was developed to segment the four cardiac chambers and EAT from cardiac MRI. Based on the resulting whole-heart segmentations, EAT was automatically partitioned into four chamber-specific subregions, voxel-wise thickness maps were reconstructed, and spatial statistics were applied to identify localized clustering patterns of EAT. Chamber-resolved and region-specific quantitative features were extracted to characterize the spatial distribution of EAT across the heart. The proposed approach was evaluated on a cohort including individuals with type 2 diabetes (T2D) and matched controls, revealing distinct T2D-associated remodeling, including increased chamber-specific burden, localized thickening, and spatial hotspot clustering in metabolically vulnerable regions. This work introduces a scalable and automated method for regional EAT phenotyping and provides spatially resolved imaging biomarkers that may support CVD research and risk stratification.

An important challenge in multi-agent reinforcement learning is partial observability, where agents cannot access the global state of the environment during execution and can only receive observations within their field of view. To address this issue, previous works typically use the dimensional-wise state, which is obtained by applying MLP or dimensional-based attention on the global state, for decision-making during training and relying on a reconstructed dimensional-wise state during execution. However, dimensional-wise states tend to divert agent attention to specific features, neglecting potential dependencies between agents, making it difficult to make optimal decisions. Moreover, the inconsistency between the states used in training and execution further increases additional errors. To resolve these issues, we propose a method called Reconstruction-Guided Policy (RGP) to reconstruct the agent-wise state, which represents the information of inter-agent relationships, as input for decision-making during both training and execution. This not only preserves the potential dependencies between agents but also ensures consistency between the states used in training and execution. We conducted extensive experiments on both discrete and continuous action environments to evaluate RGP, and the results demonstrates its superior effectiveness. Our code is public in https://anonymous.4open.science/r/RGP-9F79

The performance of offline reinforcement learning (RL) is sensitive to the proportion of high-return trajectories in the offline dataset. However, in many simulation environments and real-world scenarios, there are large ratios of low-return trajectories rather than high-return trajectories, which makes learning an efficient policy challenging. In this paper, we propose a method called Contrastive Diffuser (ContraDiff) to make full use of low-return trajectories and improve the performance of offline RL algorithms. Specifically, ContraDiff groups the states of trajectories in the offline dataset into high-return states and low-return states and treats them as positive and negative samples correspondingly. Then, it designs a contrastive mechanism to pull the planned trajectory of an agent toward high-return states and push them away from low-return states. Through the contrast mechanism, trajectories with low returns can serve as negative examples for policy learning, guiding the agent to avoid areas associated with low returns and achieve better performance. Through the contrast mechanism, trajectories with low returns provide a ``counteracting force'' guides the agent to avoid areas associated with low returns and achieve better performance. Experiments on 27 sub-optimal datasets demonstrate the effectiveness of our proposed method. Our code is publicly available at https://github.com/Looomo/contradiff.

Computerized Adaptive Testing (CAT) is a fundamental issue in intelligent education, which aims to select a relatively small number of questions to assess student’s ability. However, existing approaches often suffer from a limited selection area within the question bank, as questions without ground truth answers in the practice log are considered invalid for selection. The selection area refers to the range of questions in the question bank that have answers. To expand the selection area, we proposed a framework called Certainty-Guaranteed Environment for Computerized Adaptive Testing (CECAT). First, Simulative Interaction Module (SIM) leverages questions and their answer results in practice log in training data, so as to predict the distribution of answer result for each question without answer result in practice log. Second, α-Certainty is designed to measure the statistical similarity of the predicted distribution of answer results obtained from SIM, so as to exclude the statistically dissimilar expanded answer results. Extensive experiments on three public datasets demonstrate that CECAT outperforms twelve strong baselines in terms of assessing the student’s ability. Our code is available at https://anonymous.4open.science/r/SimCAT-F31B/README.md.

Computerized Adaptive Testing (CAT) is a burgeoning online educational technology that assesses student ability through a relatively small number of carefully selected questions. Assessing a student’s ability from his/her short question-answer sequence is a few-shot learning problem, which is currently solved by meta-learning-based methods with a bi-level structure. However, current methods using the bi-level structure have limitations, such as inefficiency due to alternating optimization between the inner level and outer level and not fully using historical students. To address these, we propose the Individualized High-Efficiency Ability Assessment for Computerized Adaptive Testing (IECAT), which introduces (1) a Student Comparison method to fully use dissimilar students by distinguishing similar and dissimilar students, (2) an Ability Matrix to fully use practice logs of historical students to get more accurate abilities, and (3) an Individual Mapping (IM) structure to improve efficiency by optimizing in its single-level structure. Extensive experiments across three public datasets demonstrate that IECAT outperforms twelve strong baselines. Furthermore, our experiments validate that IM structure consumes less training time than bilevel structure. Our code is available at https://anonymous.4open.science/r/IECAT-8FE5/IECAT/ReadMe.txt.

A question-answering (QA) simulator is a model that simulates human students QA behaviors. By leveraging QA history to estimate the probability of correctly answering a newly recommended question, the simulator enables the educational recommender systems to be trained in a simulated environment, protecting human students from the potential negative impact of low-quality recommendations. Despite its significant importance, the construction of QA simulators has not been thoroughly explored in the research domain of AI. Previous methods mainly rely on existing knowledge tracing (KT) models to construct such a simulator. However, due to the discrepancy between the KT task and the simulation task, those KT-based simulators suffer from severe bias accumulation, which limits the effectiveness of the simulation. In this paper, we propose a method called Diffusion-based Simulator (DSim), which takes advantage of diffusion to alleviate the bias accumulation. To our knowledge, DSim is the first to focus on building a QA simulator.

Mutual learning that can be seen as a derivative method of knowledge distillation takes advantages of the collective capabilities of multiple neural networks to promote the precision and stability of classification outcomes, and achieved great success in the field of computer vision. Recently, mutual learning has been exploited in the task of medical image classification. However, medical images belonging to different classes may be very similar, which may affect the classification performance of the mutual learning based methods. In this paper, we propose a novel mutual learning model, named DualDoctor, especially for the classification of medical images. DualDoctor is built by embedding the channel and spatial feature-based dynamic knowledge transfer module and the logit-based class alignment module into the vanilla mutual learning framework. The dynamic knowledge transfer module makes two sub-models sharing the critical information at the feature level, while the logit-based class alignment module enforces two sub-models to absorb the class correlation knowledge from each other at the logit level. Therefore, DualDoctor can adapt well to the characteristics of medical images so as to make more accurate classifications. The evaluation results on two public datasets, BUSI and ISIC2018, indicate that the proposed DualDoctor model performs better than the comparison methods in medical image classification tasks.

In offline reinforcement learning (RL), the performance of the learned policy highly depends on the quality of offline datasets. However, the offline dataset contains very limited optimal trajectories in many cases. This poses a challenge for offline RL algorithms, as agents must acquire the ability to transit to high-reward regions. To address this issue, we introduce Diffusionbased Trajectory Stitching (DiffStitch), a novel diffusion-based data augmentation pipeline that systematically generates stitching transitions between trajectories. DiffStitch effectively connects low-reward trajectories with high-reward trajectories, forming globally optimal trajectories and thereby mitigating the challenges faced by offline RL algorithms in learning trajectory stitching. Empirical experiments conducted on D4RL datasets demonstrate the effectiveness of our pipeline across RL methodologies. Notably, DiffStitch demonstrates substantial enhancements in the performance of one-step methods(IQL), imitation learning methods(TD3+BC) and trajectory optimization methods(DT). Our code is publicly available at https://github.com/guangheli12/DiffStitch

Squamous cell carcinoma of the head and neck is currently the eighth most common cancer worldwide. In recent years, medical researchers have proposed a promising immune checkpoint blockade treatment to treat the disease, however, only a small number of patients with advanced head and neck squamous cell carcinoma (about 13%) can benefit from immune checkpoint blockade therapy. Therefore, assessing the patient’s response to immune checkpoint blockade before treatment can help develop a treatment strategy. Tertiary lymphoid structures (TLSs) are complex structures that often appear around tumors, and their presence suggests strong immunoactivity and sensitivity to immunotherapy. Therefore, the presence or absence of TLSs is a valid indicator of the patient’s response to immune checkpoint blockade before surgery. At present, the detection methods for TLSs are all postoperative pathological examinations, but their speed is slow and aggressive. However, few studies have employed non-invasive methods to detect and assess the TLS status of cancer before surgery. In this paper, we propose a 3D convolutional neural network UDNet based on the original U-Net and Dense-Net, which can determine the presence of TLSs by using the patient’s contrast-enhanced CT image. At last, we verify the ability of the model to predict TLSs by comparing the predicting results of the model and the predicting results of three experienced clinicians. The results show that the accuracy of UDNet (72.7%) is much higher than the average accuracy (42.4%) predicted by the three experienced clinicians.

Computerized Adaptive Testing refers to an online student ability testing system. It consists of Selection Algorithm and Cognitive Diagnosis Module (CDM). The Selection Algorithm aims to carefully select a small set of questions for the newly arrived student to answer, and the CDM aims to infer the ability of the newly arrived student based on his answers to the selected questions. The CDM faces the challenge of inferring student ability based on the short question-answer sequence. The state-of-the-art approach employs a meta-learning framework to solve this challenge. Specifically, in the outer-layer of the meta-learning framework, it learns an average student ability from all students as the initial ability for the newly arrived student, while in the inner-layer of the meta-learning framework, it infers the newly arrived student’s ability from the short sequence. However, this approach suffers from two major limitations: Firstly, collaborative information between the newly arrived student and all students was not utilized. Secondly, the meta-learning framework has a slow convergence. This paper introduces Student-Adaptive Computerized Adaptive Testing (SACAT), which addresses these issues by: Firstly, use the short sequence of the newly arrived student to retrieve similar students from all students. Secondly, design a fast adaptive function that can adaptively generate an ability representation suitable for the newly arrived student from abilities of similar students. Through extensive experiments on three real-world student response datasets, we validate that SACAT can outperform existing CAT methods. Furthermore, through the fast adaptation, we show that SACAT achieves fast model convergence.

Computerized Adaptive Testing (CAT) refers to an online system that adaptively selects the best-suited question for students with various abilities based on their historical response records. Compared with traditional CAT methods based on heuristic rules, recent data-driven CAT methods obtain higher performance by learning from large-scale datasets. However, most CAT methods only focus on the quality objective of predicting the student ability accurately, but neglect concept diversity or question exposure control, which are important considerations in ensuring the performance and validity of CAT. Besides, the students' response records contain valuable relational information between questions and knowledge concepts. The previous methods ignore this relational information, resulting in the selection of sub-optimal test questions. To address these challenges, we propose a Graph-Enhanced Multi-Objective method for CAT (GMOCAT). Firstly, three objectives, namely quality, diversity and novelty, are introduced into the Scalarized Multi-Objective Reinforcement Learning framework of CAT, which respectively correspond to improving the prediction accuracy, increasing the concept diversity and reducing the question exposure. We use an Actor-Critic Recommender to select questions and optimize three objectives simultaneously by the scalarization function. Secondly, we utilize the graph neural network to learn relation-aware embeddings of questions and concepts. These embeddings are able to aggregate neighborhood information in the relation graphs between questions and concepts. We conduct experiments on three real-world educational datasets. The experimental results show that GMOCAT not only outperforms the state-of-the-art methods in the ability prediction, but also achieve superior performance in improving the concept diversity and alleviating the question exposure.

Program representation, which aims at converting program source code into vectors with automatically extracted features, is a fundamental problem in programming language processing (PLP). Recent work tries to represent programs with neural networks based on source code structures. However, such methods often focus on the syntax and consider only one single perspective of programs, limiting the representation power of models. This paper proposes a multi-view graph (MVG) program representation method. MVG pays more attention to code semantics and simultaneously includes both data flow and control flow as multiple views. These views are then combined and processed by a graph neural network (GNN) to obtain a comprehensive program representation that covers various aspects. We thoroughly evaluate our proposed MVG approach in the context of algorithm detection, an important and challenging subfield of PLP. Specifically, we use a public dataset POJ-104 and also construct a new challenging dataset ALG-109 to test our method. In experiments, MVG outperforms previous methods significantly, demonstrating our model's strong capability of representing source code.

Knowledge tracing, which estimates students' knowledge states by predicting the probability that they correctly answer questions, is an essential task for online learning platforms. It has gained much attention in the decades due to its importance to downstream tasks like learning material arrangement, etc. The previous deep learning-based methods trace students' knowledge states with the explicitly intra-student information, i.e., they only consider the historical information of individuals to make predictions. However, they neglect the inter-student information, which contains the response correctness of other students who have similar question-answering experiences, may offer some valuable clues. Based on this consideration, we propose a method called Collaborative Knowledge Tracing (CoKT) in this paper, which sufficiently exploits the inter-student information in knowledge tracing. It retrieves the sequences of peer students who have similar question-answering experiences to obtain the inter-student information, and integrates the inter-student information with the intra-student information to trace students' knowledge states and predict their correctness in answering questions. We validate the effectiveness of our method on four real-world datasets and compare it with 11 baselines. The experimental results reveal that CoKT achieves the best performance.

Knowledge tracing, which dynamically estimates students' learning states by predicting their performance on answering questions, is an essential task in online education. One typical solution for knowledge tracing is based on Recurrent Neural Networks (RNNs), which represent students' knowledge states with the hidden states of RNNs. Such type of methods normally assumes that students have the same cognition level and knowledge acquisition sensitivity on the same question. Thus, they (i) predict students' responses by referring to their knowledge states and question representations, and (ii) update the knowledge states according to the question representations and students' responses. No explicit cognition level or knowledge acquisition sensitivity is considered in the above two processes. However, in real-world scenarios, students have different understandings on a question and have various knowledge acquisition after they finish the same question. In this paper, we propose a novel model called Individual Estimation Knowledge Tracing (IEKT), which estimates the students' cognition on the question before response prediction and assesses their knowledge acquisition sensitivity on the questions before updating the knowledge state. In the experiments, we compare IEKT with 11 knowledge tracing baselines on four benchmark datasets, and the results show IEKT achieves the state-of-the-art performance.

Weakest preconditions derived from triple axiomatic semantics have been widely used to prove the correctness of programs. They can also be applied to evaluate the reliability of software. However, deducing a weakest precondition, as well as determining its propagation path, encounters challenges such as unknown constraint conditions, symbol computation and means of representation. To address these challenges, in this paper, we utilize the disjunctive normal form of if-else branch structure to capture reasonable propagation paths of the weakest precondition. Meanwhile, by removing the sequential dependencies, we demonstrate how to get the weakest precondition of loop-structure by leveraging program function. Moreover, we extensively explore three modeling characteristics (i.e., path extension, innermost connection and condition leap) for deducing the weakest precondition of structured programs. Finally, taking the definition of program node and storage structure of weakest precondition as bases, we design a serial of modeling algorithms. Based on symbol computation and recursive call technology with Depth-First Search (DFS), our algorithms can not only be used to deduce the weakest precondition, but also to capture the propagate path of the weakest precondition. Experiments illustrate the efficacy and effectiveness of our proposed models and designed deductive algorithms.