论文检索

Yang Wang 0102, Jiaqi Zhu 0001, Miaomiao Li 0007, Jiang Liu, Yilin Li 0003, Yi Yang 0060, Jiafan Li, Hongan Wang

Recently, rule-based time series classification models are widely used in safety-critical scenarios demanding strong interpretability, through providing explicit and rigorous rationales. However, due to the discrepancy between discrete rules and continuous neural networks, the generated rules are not completely consistent with the actual decision-making process, rendering users hesitant to trust the model. Additionally, existing methods learn the role (weight) of each time point independently, which is not in line with human understanding and the consecutive nature of temporal properties. In this paper, we propose a novel neuro-symbolic model named TemporalRule, aiming to automatically learn Signal Temporal Logic (STL) rules for interpretable time series classification. Our model directly optimizes the neural networks representing discrete rules via gradient grafting, producing reliable rules that can exactly determine the classification results. Notably, a temporal logical layer is designed to simulate expressive temporal operators, including one 2-predicate operator (Until) and two 2-level composite operators (EA and AE), through adaptively learning the time bounds of involved intervals. That creates consistent weights for consecutive time points, enhancing the intuitiveness of derived rules. Extensive experiments on diverse real-world datasets in safety-critical domains show that TemporalRule achieves superior and stable classification accuracy compared to state-of-the-art rule-based approaches, and the learned rules can precisely and concisely explicate the classification results, leading to a trustable model.

Mengyu Wang, Tiejun Ma, Shay B. Cohen

Stock selection, which aims to predict stock prices and identify the most profitable ones, is a crucial task in finance. While existing methods primarily focus on developing model structures and building graphs for improved selection, pre-training strategies remain underexplored in this domain. Current stock series pre-training follows methods from other areas without adapting to the unique characteristics of financial data, particularly overlooking stock-specific contextual information and the non-stationary nature of stock prices. Consequently, the latent statistical features inherent in stock data are underutilized. In this paper, we propose three novel pre-training tasks tailored to stock data characteristics: stock code classification, stock sector classification, and moving average prediction. We develop the Stock Specialized Pre-trained Transformer (SSPT) based on a two-layer transformer architecture. Extensive experimental results validate the effectiveness of our pre-training methods and provide detailed guidance on their application. Evaluations on five stock datasets, including four markets and two time periods, demonstrate that SSPT consistently outperforms the market and existing methods in terms of both cumulative investment return ratio and Sharpe ratio. Additionally, our experiments on simulated data investigate the underlying mechanisms of our methods, providing insights into understanding price series. Our code is publicly available at: https://github.com/astudentuser/Pre-training-Time-Series-Models-with-Stock-Data-Customization.

Shuangyin Li, Jihua Yang, Yixuan Wang, Shimin Di, Lei Chen 0002

Single-cell RNA sequencing (scRNA-seq) technology has emerged as a powerful tool for studying complex biological systems and diseases with high resolution. However, generating sufficient high quality scRNA-seq samples for accurate downstream analyses and ensuring reproducibility remains a challenge. Previous methods often produce low-quality samples or a limited number of useful specific cell subpopulations. To address this issue, we propose a novel Efficient Single-Cell RNA-seq Flow Diffusion (named ESCFD) method based on the Diffusion Model, capable of synthesizing large-scale, high-quality scRNA-seq samples and generating either ''holistic'' or specific cellular subpopulations within a single framework. A pre-guidance mechanism is designed for synthesizing specific cellular subpopulations of high quality, and a post-guidance mechanism was designed to accelerate the sampling of scRNA-seq samples. The ESCFD can efficiently synthesize large-scale and high-quality scRNA-seq samples for various downstream tasks, surpassing previous work with faster sampling speed. Experimental results demonstrate that the ESCFD model achieves state-of-the-art performance in cell classification and cell distribution similarity when evaluated on three scRNA-seq benchmarks, and verified the effectiveness of accelerated sampling. Visualization experiments also reveal the ESCFD's ability to synthesize specific cellular subpopulations. This innovative approach has the potential to significantly advance our understanding of complex biological systems and accelerate the development of novel therapeutic interventions and personalized medicine strategies.

Weichen Zhao, Chenguang Wang 0001, Xinyan Wang 0004, Congying Han, Tiande Guo, Tianshu Yu 0001

This paper presents an analytical study of the oversmoothing issue in diffusion-based Graph Neural Networks (GNNs). Generalizing beyond extant approaches grounded in random walk analysis or particle systems, we approach this problem through operator semigroup theory. This theoretical framework allows us to rigorously prove that oversmoothing is intrinsically linked to the ergodicity of the diffusion operator. Relying on semigroup method, we can quantitatively analyze the dynamic of graph diffusion and give a specific mathematical form of the smoothing feature by ergodicity and invariant measure of operator, which improves previous works only show existence of oversmoothing. This finding further poses a general and mild ergodicity-breaking condition, encompassing the various specific solutions previously offered, thereby presenting a more universal and theoretically grounded approach to relieve oversmoothing in diffusion-based GNNs. Additionally, we offer a probabilistic interpretation of our theory, forging a link with prior works and broadening the theoretical horizon. Our experimental results reveal that this ergodicity-breaking term effectively mitigates oversmoothing measured by Dirichlet energy, and simultaneously enhances performance in node classification tasks.

Yuanhao Pu, Defu Lian, Xiaolong Chen, Jin Chen 0008, Ze Liu, Enhong Chen

The two-tower model has become prevalent in recommender systems for its computational efficiency and robust predictive capabilities. The model usually employs two independent neural networks to encode user and item data separately, and predicts the similarity score with inner product or cosine functions, depending on which the Top-k ranked item list is generated. The optimization process typically involves a multi-label classification objective, often guided by surrogate loss functions like Softmax and One-vs-All (OvA), to enhance the recommendation performance. Despite both Softmax and OvA losses being Bayes-consistent, empirical observations reveal a significant performance gap in evaluation metrics, suggesting limitations in Bayes-consistency for analyzing loss effectiveness. To address this, we introduce ℋ-consistency into the discussion, which provides non-asymptotic and hypothesis-specific guarantees for Top-k classification within the two-tower model's hypothesis space. Through theoretical analysis, we demonstrate that Softmax and Cosine Contrastive Loss exhibit ℋ-consistency, while the OvA loss does not, explaining the observed performance discrepancies. Our findings bridge the gap between theoretical properties and practical outcomes, offering deeper insights into the optimization of two-tower models and contributing to the development of more effective recommendation systems.

Chien-Hung Chen, Chi-Shin Wu, Chu-Hsien Su, Hsin-Hsi Chen

Timely understanding of a patient’s clinical course is crucial for effective treatment. Extracting course-related information, such as temporal and medical events, from unstructured medical records is both challenging and time-consuming, especially when relying on manual identification by physicians. We introduce TimelyMed, a system powered by a locally deployed large language model (LLM) that ensures data security while efficiently organizing key psychiatric events and their corresponding temporal information. Additionally, our system is attributed, allowing clinicians to not only categorize events but also trace them back to their original textual descriptions, ensuring transparency and interpretability in clinical decision-making. By organizing temporal and medical event information into timelines, our system enables physicians to quickly grasp a patient’s medical history while effectively reducing their cognitive burden.

Kushal Kanwar, Dushyant Singh Chauhan, Gopendra Vikram Singh, Asif Ekbal

Memes are popular in the modern world and are distributed primarily for entertainment. However, harmful ideologies such as misogyny can be propagated through innocent-looking memes. The detection and understanding of why a meme is misogynous is a research challenge due to its multimodal nature (image and text) and its nuanced manifestations across different societal contexts. We introduce a novel multimodal approach, namely, MM-Misogyny to detect, categorize, and explain misogynistic content in memes. MM-Misogyny processes text and image modalities separately and unifies them into a multimodal context through a cross-attention mechanism. The resulting multimodal context is then easily processed for labeling, categorization, and explanation via a classifier and Large Language Model (LLM). The evaluation of the proposed model is performed on a newly curated dataset (What’s Beneath Misogynous Stereotyping (WBMS)) created by collecting misogynous memes from cyberspace and categorizing them into four categories, namely, Kitchen, Leadership, Working, and Shopping. The model not only detects and classifies misogyny, but also provides a granular understanding of how misogyny operates in operates in domains of life. The results demonstrate the superiority of our approach compared to existing methods. The code and dataset are available at https://github.com/Misogyny.

Zirong Chen, Ziyan An, Jennifer Reynolds, Kristin Mullen, Stephen Maritini, Meiyi Ma

Emergency response services are critical to public safety, with 9-1-1 call-takers playing a key role in ensuring timely and effective emergency operations. To ensure call-taking performance consistency, quality assurance is implemented to evaluate and refine call-takers' skillsets. However, traditional human-led evaluations struggle with high call volumes, leading to low coverage and delayed assessments. We introduce LogiDebrief, an AI-driven framework that automates traditional 9-1-1 call debriefing by integrating Signal-Temporal Logic (STL) with Large Language Models (LLMs) for fully-covered rigorous performance evaluation. LogiDebrief formalizes call-taking requirements as logical specifications, enabling systematic assessment of 9-1-1 calls against procedural guidelines. It employs a three-step verification process: (1) contextual understanding to identify responder types, incident classifications, and critical conditions; (2) STL-based runtime checking with LLM integration to ensure compliance; and (3) automated aggregation of results into quality assurance reports. Beyond its technical contributions, LogiDebrief has demonstrated real-world impact. Successfully deployed at Metro Nashville Department of Emergency Communications, it has assisted in debriefing 1,701 real-world calls, saving 311.85 hours of active engagement. Empirical evaluation with real-world data confirms its accuracy, while a case study and extensive user study highlight its effectiveness in enhancing call-taking performance.

Xiaoguang Wang, Chenxu Wang, Luyue Zhang, Xiaole Wang, Mengqin Wang, Huanlong Liu, Tao Qin

Financial fraud detection is critical for market transparency and regulatory compliance. Existing methods often ignore the temporal patterns in financial data, which are essential for understanding dynamic financial behaviors and detecting fraud. Moreover, they also treat companies as independent entities, overlooking the valuable interrelationships. To address these issues, we propose ACRF-RNN, a Recurrent Neural Network (RNN) with Attention-based Conditional Random Field (CRF) for fraud detection. Specifically, we use an RNN with a sliding window to capture temporal dependencies from historical data, and an attention-based CRF feature transformer to model inter-company relationships. This transforms raw financial data into optimized features, fed into a multi-layer perceptron for classification. Besides, we also use the focal loss to alleviate the class imbalance problem caused by rare fraudulent cases. This work presents a novel real-world dataset to evaluate the performance of ACRF-RNN. Extensive experiments show that ACRF-RNN outperforms the state-of-the-art methods by 15.28% in KS and 4.04% in Recall. Data and code are available at: https://github.com/XNetLab/ACRF-RNN.git.

Yuya Yoshikawa, Masanari Kimura, Ryotaro Shimizu, Yuki Saito

Techniques that explain the predictions of black-box machine learning models are crucial to make the models transparent, thereby increasing trust in AI systems. The input features to the models often have a nested structure that consists of high- and low-level features, and each high-level feature is decomposed into multiple low-level features. For such inputs, both high-level feature attributions (HiFAs) and low-level feature attributions (LoFAs) are important for better understanding the model's decision. In this paper, we propose a model-agnostic local explanation method that effectively exploits the nested structure of the input to estimate the two-level feature attributions simultaneously. A key idea of the proposed method is to introduce the consistency property that should exist between the HiFAs and LoFAs, thereby bridging the separate optimization problems for estimating them. Thanks to this consistency property, the proposed method can produce HiFAs and LoFAs that are both faithful to the black-box models and consistent with each other, using a smaller number of queries to the models. In experiments on image classification in multiple instance learning and text classification using language models, we demonstrate that the HiFAs and LoFAs estimated by the proposed method are accurate, faithful to the behaviors of the black-box models, and provide consistent explanations.

Jielong Lu, Zhihao Wu, Jiajun Yu, Jiajun Bu, Haishuai Wang

Integrating multi-omics datasets through data-driven analysis offers a comprehensive understanding of the complex biological processes underlying various diseases, particularly cancer. Graph Neural Networks (GNNs) have recently demonstrated remarkable ability to exploit relational structures in biological data, enabling advances in multi-omics integration for cancer subtype classification. Existing approaches often neglect the intricate coupling between heterogeneous omics, limiting their capacity to resolve subtle cancer subtype heterogeneity critical for precision oncology. To address these limitations, we propose a framework named Graph Transformer for Multi-omics Cancer Subtype Classification (GTMancer). This framework builds upon the GNN optimization problem and extends its application to complex multi-omics data. Specifically, our method leverages contrastive learning to embed multi-omics data into a unified semantic space. We unroll the multiplex graph optimization problem in that unified space and introduce dual sets of attention coefficients to capture structural graph priors both within and among multi-omics data. This approach enables global omics information to guide the refining of the representations of individual omics. Empirical experiments on seven real-world cancer datasets demonstrate that GTMancer outperforms existing state-of-the-art algorithms.

Rui Yan, Jin Wang, Hongyu Qu, Xiaoyu Du, Dong Zhang, Jinhui Tang, Tieniu Tan

Recently, adapting Vision Language Models (VLMs) to zero-shot visual classification by tuning class embedding with a few prompts (Test-time Prompt Tuning, TPT) or replacing class names with generated visual samples (support-set) has shown promising results. However, TPT cannot avoid the semantic gap between modalities while the support-set cannot be tuned. To this end, we draw on each other's strengths and propose a novel framework, namely TEst-time Support-set Tuning for zero-shot Video Classification (TEST-V). It first dilates the support-set with multiple prompts (Multi-prompting Support-set Dilation, MSD) and then erodes the support-set via learnable weights to mine key cues dynamically (Temporal-aware Support-set Erosion, TSE). Specifically, i) MSD expands the support samples for each class based on multiple prompts inquired from LLMs to enrich the diversity of the support-set. ii) TSE tunes the support-set with factorized learnable weights according to the temporal prediction consistency in a self-supervised manner to dig pivotal supporting cues for each class. TEST-V achieves state-of-the-art results across four benchmarks and shows good interpretability.

Yongqi Wang, Xinxiao Wu, Shuo Yang

Open-vocabulary video visual relationship detection aims to detect objects and their relationships in videos without being restricted by predefined object or relationship categories. Existing methods leverage the rich semantic knowledge of pre-trained vision-language models such as CLIP to identify novel categories. They typically adopt a cascaded pipeline to first detect objects and then classify relationships based on the detected objects, which may lead to error propagation and thus suboptimal performance. In this paper, we propose Mutual EnhancemenT of Objects and Relationships (METOR), a query-based unified framework to jointly model and mutually enhance object detection and relationship classification in open-vocabulary scenarios. Under this framework, we first design a CLIP-based contextual refinement encoding module that extracts visual contexts of objects and relationships to refine the encoding of text features and object queries, thus improving the generalization of encoding to novel categories. Then we propose an iterative enhancement module to alternatively enhance the representations of objects and relationships by fully exploiting their interdependence to improve recognition performance. Extensive experiments on two public datasets, VidVRD and VidOR, demonstrate that our framework achieves state-of-the-art performance. Codes are at https://github.com/wangyongqi558/METOR.

Feng Luan, Jiarui Hu, Changshi Zhou, Zhipeng Wang, Jiguang Yue, Yanmin Zhou, Bin He

Point cloud classification is critical for three-dimensional scene understanding. However, in real-world scenarios, depth cameras often capture partial, single-view point clouds of objects with different poses, making their accurate classification a challenge. In this paper, we propose a novel point cloud classification network that captures the detailed spatial structure of objects by constructing tetrahedra, which is different from point-wise operations. Specifically, we propose a RISpaNet block to extract rotation-invariant features. A rotation-invariant property generation module is designed in RISpaNet for constructing rotation-invariant tetrahedron properties (RITPs). Meanwhile, a multi-scale pooling module and a hybrid encoder are used to process RITPs to generate integrated rotation-invariant features. Further, for single-view point clouds, a complete point cloud auxiliary branch and a part-whole correlation module are jointly employed to obtain complete point cloud features from partial point clouds. Experimental results show that this network performs better than other state-of-the-art methods, evaluated on four public datasets. We achieved an overall accuracy of 94.7% (+2.0%) on ModelNet40, 93.4% (+5.9%) on MVP, 94.7% (+6.3%) on PCN and 94.8% (+1.7%) on ScanObjectNN. Our project website is https://luxurylf.github.io/RISpaNet_project/.

Ming-Hui Liu, Harry Cheng, Tianyi Wang, Xin Luo, Xin-Shun Xu

Deepfake detection models often struggle with generalization to unseen datasets, manifesting as misclassifying real instances as fake in target domains. This is primarily due to an overreliance on forgery artifacts and a limited understanding of real faces. To address this challenge, we propose a novel approach RealID to enhance generalization by learning a comprehensive concept of real faces while assessing the probabilities of belonging to the real and fake classes independently. RealID comprises two key modules: the Real Concept Capture Module (RealC^2) and the Independent Dual-Decision Classifier (IDC). With the assistance of a Multi-Real Memory, RealC^2 maintains various prototypes for real faces, allowing the model to capture a comprehensive concept of real class. Meanwhile, IDC redefines the classification strategy by making independent decisions based on the concept of the real class and the presence of forgery artifacts. Through the combined effect of the above modules, the influence of forgery-irrelevant patterns is alleviated, and extensive experiments on five widely used datasets demonstrate that RealID significantly outperforms existing state-of-the-art methods, achieving a 1.74% improvement in average accuracy.

Jinglin Huang, Maoqiang Wu, Peichun Li, Wen Wu, Rong Yu

Cross-view geo-localization is a crucial task with diverse applications, yet it remains challenging due to the significant variations in viewpoints and visual appearances between images from different perspectives. While recent advancements have been made, existing methods often suffer from high model complexity, excessive resource consumption, and the impact of sample learning difficulty on optimization. To overcome these limitations, we optimize the Vision Mamba (Vim) model, built on a State Space Model (SSM) architecture, by replacing the traditional classification head with Channel Group Pooling (CGP) for efficient feature integration. This optimization reduces model parameters by 1.5% and computational complexity by 0.4%. Additionally, we propose a novel Dynamic Weighted Batch-tuple Loss (DWBL) to dynamically adjust the weighting of negative samples, improving model performance. By combining CGP and DWBL, we develop an efficient end-to-end network, VimGeo, which achieves state-of-the-art performance with enhanced computational efficiency. Specifically, VimGeo achieves a Recall@1 of 81.67% on the CVACT_test dataset, outperforming prior approaches. Extensive experiments on CVUSA, CVACT, and VIGOR datasets validate VimGeo's effectiveness and competitiveness in cross-view geo-localization tasks, achieving the leading results among sequence modeling-based methods. The implementation is available at: https://github.com/VimGeoTeam/VimGeo.

Wenxuan Ge, Peng Huang, Rui Yan, Hongyu Qu, Guosen Xie, Xiangbo Shu

Adapting pre-trained vision-language models to downstream tasks has emerged as a novel paradigm for zero-shot learning. Existing test-time adaptation (TTA) methods such as TPT attempt to fine-tune visual or textual representations to accommodate downstream tasks but still require expensive optimization costs. To this end, Training-free Dynamic Adapter (TDA) maintains a cache containing visual features for each category in a parameter-free manner and measures sample confidence based on prediction entropy of test samples. Inspired by TDA, this work aims to develop the first training-free adapter for zero-shot video classification. Capturing the intrinsic temporal relationships within video data to construct and maintain the video cache is key to extending TDA to the video domain. In this work, we propose a reliable and diverse Hierarchical Adapter for zero-shot video classification, which consists of Frame-level Cache Refiner and Video-level Cache Updater. Before each video sample enters the corresponding cache, it needs to be refined at frame level based on prediction entropy and temporal probability difference. Due to the limited capacity of the cache, we update the cache during inference based on the principle of diversity. Experiments on four popular video classification benchmarks demonstrate the effectiveness of Hierarchical Adapter. The code is available at https://github.com/Gwxer/Hierarchical-Adapter.

Chunjiang Wang, Kun Zhang, Yandong Liu, Zhiyang He, Xiaodong Tao, S. Kevin Zhou

The concept bottleneck model (CBM), as a technique improving interpretability via linking predictions to human-understandable concepts, makes high-risk and life-critical medical image classification credible. Typically, existing CBM methods associate the final layer of visual encoders with concepts to explain the model’s predictions. However, we empirically discover the phenomenon of concept preference variation, that is, the concepts are preferably associated with the features at different layers than those only at the final layer; yet a blind last-layer-based association neglects such a preference variation and thus weakens the accurate correspondences between features and concepts, impairing model interpretability. To address this issue, we propose a novel Multi-layer Visual Preference-enhanced Concept Bottleneck Model (MVP-CBM), which comprises two key novel modules: (1) intra-layer concept preference modeling, which captures the preferred association of different concepts with features at various visual layers, and (2) multi-layer concept sparse activation fusion, which sparsely aggregates concept activations from multiple layers to enhance performance. Thus, by explicitly modeling concept preferences, MVP-CBM can comprehensively leverage multi-layer visual information to provide a more nuanced and accurate explanation of model decisions. Extensive experiments on several public medical classification benchmarks demonstrate that MVP-CBM achieves state-of-the-art accuracy and interoperability, verifying its superiority. Code is available at https://github.com/wcj6/MVP-CBM.

Sanchit Sinha, Guangzhi Xiong, Aidong Zhang

As Vision Transformers (ViTs) are increasingly adopted in sensitive vision applications, there is a growing demand for improved interpretability. This has led to efforts to forward-align these models with carefully annotated abstract, human-understandable semantic entities - concepts. Concepts provide global rationales to the model predictions and can be quickly understood/intervened on by domain experts. Most current research focuses on designing model-agnostic, plug-and-play generic concept-based explainability modules that do not incorporate the inner workings of foundation models (e.g., inductive biases, scale invariance, etc.) during training. To alleviate this issue for ViTs, in this paper, we propose ASCENT-ViT, an attention-based, concept learning framework that effectively composes scale and position-aware representations from multiscale feature pyramids and ViT patch representations, respectively. Further, these representations are aligned with concept annotations through attention matrices - which incorporate spatial and global (semantic) concepts. ASCENT-ViT can be utilized as a classification head on top of standard ViT backbones for improved predictive performance and accurate and robust concept explanations as demonstrated on five datasets, including three widely used benchmarks (CUB, Pascal APY, Concept-MNIST) and two real-world datasets (AWA2, KITS). An appendix of the paper with more comprehensive results is available at https://arxiv.org/abs/2501.09221.

Rongxin Ouyang, Kokil Jaidka, Subhayan Mukerjee, Guangyu Cui

The prevalence of multi-modal content on social media complicates automated moderation strategies. This calls for an enhancement in multi-modal classification and a deeper understanding of understated meanings in images and memes. Although previous efforts have aimed at improving model performance through fine-tuning, few have explored an end-to-end optimization pipeline that accounts for modalities, prompting, labelling, and fine-tuning. In this study, we propose an end-to-end conceptual framework for model opti- mization in complex tasks. Experiments support the efficacy of this traditional yet novel framework, achieving the highest accuracy and AUROC. Ablation experiments demonstrate that isolated optimisations are not ineffective on their own.