We introduce the novel problem of benchmarking fraud detectors on private graph-structured data. Currently, many types of fraud are managed in part by automated detection algorithms that operate over graphs. We consider the scenario where a data holder wishes to outsource development of fraud detectors to third parties (e.g., vendors or researchers). The third parties submit their fraud detectors to the data holder, who evaluates these algorithms on a private dataset and then publicly communicates the results. We propose a realistic privacy attack on this system that allows an adversary to de-anonymize individuals' data based only on the evaluation results. In simulations of a privacy-sensitive benchmark for facial recognition algorithms by the National Institute of Standards and Technology (NIST), our attack achieves near perfect accuracy in identifying whether individuals' data is present in a private dataset, with a True Positive Rate of 0.98 at a False Positive Rate of 0.00. We then study how to benchmark algorithms while satisfying a formal differential privacy (DP) guarantee. We empirically evaluate two classes of solutions: subsample-and-aggregate and DP synthetic graph data. We demonstrate through extensive experiments that current approaches fail to provide utility when guaranteeing DP. Our results indicate that the error arising from DP trades off between bias from distorting graph structure and variance from adding random noise. Current methods lie on different points along this bias-variance trade-off, but more complex methods tend to require high-variance noise addition, undermining utility.
论文检索
输入标题、作者或关键词，从 12,319 篇学术成果中精准定位
Spatial-temporal data, fundamental to many intelligent applications, reveals dependencies indicating causal links between present measurements at specific locations and historical data at the same or other locations. Within this context, adaptive spatial-temporal graph neural networks (ASTGNNs) have emerged as valuable tools for modelling these dependencies, especially through a data-driven approach rather than pre-defined spatial graphs. While this approach offers higher accuracy, it presents increased computational demands. Addressing this challenge, this paper delves into the concept of localisation within ASTGNNs, introducing an innovative perspective that spatial dependencies should be dynamically evolving over time. We introduce DynAGS, a localised ASTGNN framework aimed at maximising efficiency and accuracy in distributed deployment. This framework integrates dynamic localisation, time-evolving spatial graphs, and personalised localisation, all orchestrated around the Dynamic Graph Generator, a light-weighted central module leveraging cross attention. The central module can integrate historical information in a node-independent manner to enhance the feature representation of nodes at the current moment. This improved feature representation is then used to generate a dynamic sparse graph without the need for costly data exchanges, and it supports personalised localisation. Performance assessments across two core ASTGNN architectures and nine real-world datasets from various applications reveal that DynAGS outshines current benchmarks, underscoring that the dynamic modelling of spatial dependencies can drastically improve model expressibility, flexibility, and system efficiency, especially in distributed settings.
Human trajectory data, which plays a crucial role in various applications such as crowd management and epidemic prevention, is challenging to obtain due to practical constraints and privacy concerns. In this context, synthetic human trajectory data is generated to simulate as close as possible to real-world human trajectories, often under summary statistics and distributional similarities. However, these similarities oversimplify complex human mobility patterns (a.k.a. ''Datasaurus''), resulting in intrinsic biases in both generative model design and benchmarks of the generated trajectories. Against this background, we propose MIRAGE, a huMan-Imitative tRAjectory GenErative model designed as a neural Temporal Point Process integrating an Exploration and Preferential Return model. It imitates the human decision-making process in trajectory generation, rather than fitting any specific statistical distributions as traditional methods do, thus avoiding the Datasaurus issue. We also propose a comprehensive task-based evaluation protocol beyond Datasaurus to systematically benchmark trajectory generative models on four typical downstream tasks, integrating multiple techniques and evaluation metrics for each task, to assess the ultimate utility of the generated trajectories. We conduct a thorough evaluation of MIRAGE on three real-world user trajectory datasets against a sizeable collection of baselines. Results show that compared to the best baselines, MIRAGE-generated trajectory data not only achieves the best statistical and distributional similarities with 59.0-67.7% improvement, but also yields the best performance in the task-based evaluation with 10.9-33.4% improvement. A series of ablation studies also validate the key design choices of MIRAGE.
In real-world applications, node classification on graphs often faces the challenge of class imbalance, where majority classes dominate training, resulting in biased model performance. Traditional Graph Neural Networks (GNNs) often struggle in such scenarios, as they tend to overfit to majority classes while underrepresenting minority classes. Existing solutions, which either prioritize nodes based on class size or synthesize new nodes for minority classes, often fall short of effectively addressing this imbalance issue. This paper introduces a novel approach to class-imbalanced node classification by utilizing a balanced meta-set for importance measurement, where a training node is considered significant if it enhances model performance under an unbiased setting. Our method identifies important nodes that can counteract class imbalance and utilizes them for model training, allowing for fine-grained and dynamic node selection throughout the training process. We theoretically derive a formula to directly assess node importance, reducing computational overhead and providing an intuitive threshold for node selection. Guided by this metric, we develop a novel framework that filters valuable labeled, unlabeled, and synthetic nodes that enhance model performance in an unbiased context. A key advantage of this framework is its separation of the synthetic node generation process from the filtering process, ensuring compatibility with various node generation techniques. Furthermore, we introduce a strategy to construct a high-quality meta-set that closely approximates the overall feature distribution, ensuring robust representation of each class. We evaluate our framework, NodeImport, across multiple benchmark datasets using popular GNN architectures, demonstrating its superiority over state-of-the-art baselines. Our results highlight the flexibility and effectiveness of the framework in mitigating class imbalance, leading to improved node classification outcomes. The source code is available at https://github.com/NanChanNN/NodeImport.
Prompt engineering enables Large Language Models (LLMs) to perform a variety of tasks. However, lengthy prompts significantly increase computational complexity and economic costs. To address this issue, prompt compression reduces prompt length while maintaining LLM response quality. To support rapid implementation and standardization, we present the Prompt Compression Toolkit (PCToolkit), a unified plug-and-play framework for LLM prompt compression. PCToolkit integrates state-of-the-art compression algorithms, benchmark datasets, and evaluation metrics, enabling systematic performance analysis. Its modular architecture simplifies customization, offering portable interfaces for seamless incorporation of new datasets, metrics, and compression methods. Our code is available at https://github.com/3DAgentWorld/Toolkit-for-Prompt-Compression. Our demo is at https://huggingface.co/spaces/CjangCjengh/Prompt-Compression-Toolbox.
Visually Rich Document Understanding (VRDU) has emerged as a critical field in document intelligence, enabling automated extraction of key information from complex documents across domains such as medical, financial, and educational applications. However, form-like documents pose unique challenges due to their complex layouts, multi-stakeholder involvement, and high structural variability. Addressing these issues, the VRD-IU Competition was introduced, focusing on extracting and localizing key information from multi-format forms within the Form-NLU dataset, which includes digital, printed, and handwritten documents. This paper presents insights from the competition, which featured two tracks: Track A, emphasizing entity-based key information retrieval, and Track B, targeting end-to-end key information localization from raw document images. With over 20 participating teams, the competition showcased various state-of-the-art methodologies, including hierarchical decomposition, transformer-based retrieval, multimodal feature fusion, and advanced object detection techniques. The top-performing models set new benchmarks in VRDU, providing valuable insights into document intelligence.
Machine unlearning, the process of removing specific data influences from Machine Learning models, is critical for complying with regulations like the GDPR's right to be forgotten and addressing copyright disputes in large models. Despite its rising importance, the field still lacks standardized tools, hindering reproducibility and evaluation. Here, we present, in an extensive way, ERASURE, a unified framework enabling reproducibility by implementing common unlearning techniques, evaluation metrics, and dedicated datasets. ERASURE advances research, ensures solution comparability, and facilitates reproducibility, addressing future legal and ethical challenges in data management.
Managing novelty in perception-based human activity recognition (HAR) is critical in realistic settings to improve task performance over time and ensure solution generalization outside of prior seen samples. Novelty manifests in HAR as unseen samples, activities, objects, environments, and sensor changes, among other ways. Novelty may be task-relevant, such as a new class or new features, or task-irrelevant resulting in nuisance novelty, such as never before seen noise, blur, or distorted video recordings. To perform HAR optimally, algorithmic solutions must be tolerant to nuisance novelty, and learn over time in the face of novelty. This paper 1) formalizes the definition of novelty in HAR building upon the prior definition of novelty in classification tasks, 2) proposes an incremental open world learning (OWL) protocol and applies it to the Kinetics datasets to generate a new benchmark KOWL-718, 3) analyzes the performance of current stateof-the-art HAR models when novelty is introduced over time, 4) provides a containerized and packaged pipeline for reproducing the OWL protocol and for modifying for any future updates to Kinetics. The experimental analysis includes an ablation study of how the different models perform under various conditions as annotated by Kinetics-AVA. The code may be used to analyze different annotations and subsets of the Kinetics datasets in an incremental open world fashion, as well as be extended as further updates to Kinetics are released.
By virtue of its great utility in solving real-world problems, optimization modeling has been widely employed for optimal decision-making across various sectors, but it requires substantial expertise from operations research professionals. With the advent of large language models (LLMs), new opportunities have emerged to automate the procedure of mathematical modeling. This survey presents a comprehensive and timely review of recent advancements that cover the entire technical stack, including data synthesis and fine-tuning for the base model, inference frameworks, benchmark datasets, and performance evaluation. In addition, we conducted an in-depth analysis on the quality of benchmark datasets, which was found to have a surprisingly high error rate. We cleaned the datasets and constructed a new leaderboard with fair performance evaluation in terms of base LLM model and datasets. We also build an online portal that integrates resources of cleaned datasets, code and paper repository to benefit the community. Finally, we identify limitations in current methodologies and outline future research opportunities.
Retina images provide a noninvasive view of the central nervous system and microvasculature, making it essential for clinical applications. Changes in the retina often indicate both ophthalmic and systemic diseases, aiding in diagnosis and early intervention. While deep learning algorithms have advanced retina image analysis, a comprehensive review of related datasets, tasks, and benchmarking is still lacking. In this survey, we systematically categorize existing retina image datasets based on their available data modalities, and review the tasks these datasets support in multimodal retina image analysis. We also explain key evaluation metrics used in various retina image analysis benchmarks. By thoroughly examining current datasets and methods, we highlight the challenges and limitations in existing benchmarks and discuss potential research topics in the field. We hope this work will guide future retina analysis methods and promote the shared use of existing data across different tasks.
A Survey on Temporal Interaction Graph Representation Learning: Progress, Challenges, and Opportunities
PDF ↗Temporal interaction graphs (TIGs), defined by sequences of timestamped interaction events, have become ubiquitous in real-world applications due to their capability to model complex dynamic system behaviors. As a result, temporal interaction graph representation learning (TIGRL) has garnered significant attention in recent years. TIGRL aims to embed nodes in TIGs into low-dimensional representations that effectively preserve both structural and temporal information, thereby enhancing the performance of downstream tasks such as classification, prediction, and clustering within constantly evolving data environments. In this paper, we begin by introducing the foundational concepts of TIGs and emphasizing the critical role of temporal dependencies. We then propose a comprehensive taxonomy of state-of-the-art TIGRL methods, systematically categorizing them based on the types of information utilized during the learning process to address the unique challenges inherent to TIGs. To facilitate further research and practical applications, we curate the source of datasets and benchmarks, providing valuable resources for empirical investigations. Finally, we examine key open challenges and explore promising research directions in TIGRL, laying the groundwork for future advancements that have the potential to shape the evolution of this field.
Large language models (LLMs) have achieved remarkable successes on various tasks. However, recent studies have found that there are still significant challenges to the logical reasoning abilities of LLMs, which can be categorized into the following two aspects: (1) Logical question answering: LLMs often fail to generate the correct answer within a complex logical problem which requires sophisticated deductive, inductive or abductive reasoning given a collection of premises and constrains. (2) Logical consistency: LLMs are prone to producing responses contradicting themselves across different questions. For example, a state-of-the-art question-answering LLM Macaw, answers Yes to both questions Is a magpie a bird? and Does a bird have wings? but answers No to Does a magpie have wings?. To facilitate this research direction, we comprehensively investigate the most cutting-edge methods and propose a detailed taxonomy. Specifically, to accurately answer complex logic questions, previous methods can be categorized based on reliance on external solvers, prompts, and fine-tuning. To avoid logical contradictions, we discuss concepts and solutions of various logical consistencies, including implication, negation, transitivity, factuality consistencies, and their composites. In addition, we review commonly used benchmark datasets and evaluation metrics, and discuss promising research directions, such as extending to modal logic to account for uncertainty and developing efficient algorithms that simultaneously satisfy multiple logical consistencies.
Text-to-music (TTM) generation, which converts textual descriptions into audio, opens up innovative avenues for multimedia creation. Achieving high quality and diversity in this process demands extensive, high-quality data, which are often scarce in available datasets. Most open-source datasets frequently suffer from issues like low-quality waveforms and low text-audio consistency, hindering the advancement of music generation models. To address these challenges, we propose a novel quality-aware training paradigm for generating high-quality, high-musicality music from large-scale, quality-imbalanced datasets. Additionally, by leveraging unique properties in the latent space of musical signals, we adapt and implement a masked diffusion transformer (MDT) model for the TTM task, showcasing its capacity for quality control and enhanced musicality. Furthermore, we introduce a three-stage caption refinement approach to address low-quality captions' issue. Experiments show state-of-the-art (SOTA) performance on benchmark datasets including MusicCaps and the Song-Describer Dataset with both objective and subjective metrics. Demo audio samples are available at https://qa-mdt.github.io/, code and pretrained checkpoints are open-sourced at https://github.com/ivcylc/OpenMusic.
Enhancing Online Climate Discourse: A Two-Stage Framework for Climate Content Categorization and Moderation
PDF ↗Climate change is one of the most pressing global challenges that requires urgent adaptation and resilience efforts, highlighting the need for both scientific solutions and effective communication. In the digital age, online content plays a key role in shaping climate narratives. Therefore, previous research has mainly focused on public perception or categorized content by topics such as impacts, mitigation, policy, etc. Despite these efforts, identifying discussions that address climate change adaptation is crucial for monitoring resilience and assessing public sentiment, while recognizing denial narratives helps combat misinformation. Moreover, the public's exposure to online climate content can either lead to or hinder climate action, emphasizing the need for climate content moderation. To address these issues, we propose a novel multi-stage framework where stage 1 categorizes climate-related content into adaptation, resilience, and denial while stage 2 moderates content by enhancing or intervening based on its alignment with climate goals. We present a novel dataset by manually annotating publicly available tweets and news articles into different climate categories with the help of a taxonomy developed by domain experts. Extensive experiments with benchmark climate and other domain datasets validate the efficacy of our prediction stage, while human and external evaluations confirm the relevance of our moderation stage.
We propose the Moral Compass benchmark, a point of reference for incorporating ethical cognition in AI. It has four key contributions. A Moral Decision Dataset (MDD) that captures cases with ethical ambiguity, along with parameters that aid moral decision-making. It is created using a methodology that leverages the use of Large Language Models (LLMs) and seed data from real-world sources which are processed, summarized, and augmented. We also introduce a Moral Decision Knowledge Graph (MDKG) that is created using feature mappings of the relational dataset MDD to facilitate efficient querying. To demonstrate the validity and robustness of this dataset, we introduce an Ethics Scoring Algorithm (ESA) that makes use of the parameters defined in the dataset to calculate ethical scores for isolated actions. Furthermore, ESA is extended by the novel concept of context-sensitive thresholding (CST) to discretize grey areas to resolve ethical dilemmas with explainable results. This work aims to facilitate ethical cognition in AI systems that are deployed in various important sections of society through a clear methodology, modular development, and broad applicability.
MolHFCNet: Enhancing Molecular Graph Representations with Hierarchical Feature Combining and Hybrid Pretraining
PDF ↗Efficient molecular property prediction is crucial in bioinformatics and cheminformatics, with applications in drug discovery, materials science, and chemical engineering. This paper introduces MolHFCNet, a graph neural network designed to enhance molecular representation learning. At its core, the n-Hierarchical Features Combining (n-HFC) module aggregates information across multiple hierarchical feature spaces, effectively capturing both local and global graph structures. Unlike conventional models, n-HFC maintains computational complexity comparable to a single full-dimensional graph layer while supporting either 2D or 3D molecular graphs, ensuring flexibility across tasks. Furthermore, we propose a novel graph pretraining strategy that integrates predictive and contrastive learning, enabling the model to capture local chemical interactions and global molecular contexts for robust embeddings. Experimental results on benchmark datasets demonstrate MolHFCNet’s superior accuracy and efficiency compared to state-of-the-art methods, highlighting the potential of high-order hierarchical feature learning for advancing molecular graph analysis. Our code is available at https://github.com/ndlongvn/MolHFCNet.
DeepFeatIoT: Unifying Deep Learned, Randomized, and LLM Features for Enhanced IoT Time Series Sensor Data Classification in Smart Industries
PDF ↗Internet of Things (IoT) sensors are ubiquitous technologies deployed across smart cities, industrial sites, and healthcare systems. They continuously generate time series data that enable advanced analytics and automation in industries. However, challenges such as the loss or ambiguity of sensor metadata, heterogeneity in data sources, varying sampling frequencies, inconsistent units of measurement, and irregular timestamps make raw IoT time series data difficult to interpret, undermining the effectiveness of smart systems. To address these challenges, we propose a novel deep learning model, DeepFeatIoT, which integrates learned local and global features with non-learned randomized convolutional kernel-based features and features from large language models (LLMs). This straightforward yet unique fusion of diverse learned and non-learned features significantly enhances IoT time series sensor data classification, even in scenarios with limited labeled data. Our model's effectiveness is demonstrated through its consistent and generalized performance across multiple real-world IoT sensor datasets from diverse critical application domains, outperforming state-of-the-art benchmark models. These results highlight DeepFeatIoT's potential to drive significant advancements in IoT analytics and support the development of next-generation smart systems.
The rapid advancement of large language models (LLMs) has led to the widespread adoption of video-language models (VLMs) across various domains. However, VLMs are often hindered by their limited semantic discrimination capability, exacerbated by the limited diversity and biased sample distribution of most video-language datasets. This limitation results in a biased understanding of the semantics between visual concepts, leading to hallucinations. To address this challenge, we propose a Multi-level Multimodal Alignment (MMA) framework that leverages a text encoder and semantic discriminative loss to achieve multi-level alignment. This enables the model to capture both low-level and high-level semantic relationships, thereby reducing hallucinations. By incorporating language-level alignment into the training process, our approach ensures stronger semantic consistency between video and textual modalities. Furthermore, we introduce a two-stage progressive training strategy that exploits larger and more diverse datasets to enhance semantic alignment and better capture general semantic relationships between visual and textual modalities. Our comprehensive experiments demonstrate that the proposed MMA method significantly mitigates hallucinations and achieves state-of-the-art performance across multiple video-language tasks, establishing a new benchmark in the field.
Behavior Trees (BTs) are a widely used control architecture in robotics, renowned for their robustness and safety, which are especially crucial for everyday service robots. Recently, several methods have been proposed to automatically plan BTs to accomplish specific tasks. However, existing research in BT planning lacks two main aspects: (1) the absence of a standard platform for modeling and planning BTs, along with testing benchmarks; and (2) insufficient metrics for a comprehensive evaluation of BT planning algorithms. In this paper, we propose Behavior Tree Planning Gym (BTPG), the first platform and benchmark for BT planning in everyday service robots. In BTPG, behavior nodes are represented by predicate logic, and objects are categorized to better define the predicate domains and action models. The BT planning problem is then formulated in the STRIPS style. We support four environments and three simulators with different action models, which cover most of the needs of everyday service activities. We design a dataset generator for each environment and test three state-of-the-art BT planning algorithms, as well as one proposed by us, using various common metrics. In addition, we design three advanced metrics, planning progress, region distance, and execution robustness, to gain deeper insights into these BT planning algorithms. With a standard test benchmark, we hope BTPG can inspire and accelerate progress in the field of BT planning. Our codes are available at https://github.com/DIDS-EI/BTPG.
DGL: Dynamic Global-Local Information Aggregation for Scalable VRP Generalization with Self-Improvement Learning
PDF ↗The Vehicle Routing Problem (VRP) is a critical combinatorial optimization problem with wide-reaching real-world applications, particularly in logistics, transportation. While neural network-based VRP solvers have shown impressive results on test instances similar to training data, their performance often degrades when faced with varying scales and unseen distributions, limiting their practical applicability. To overcome these limitations, we introduce DGL (Dynamic Global-Local Information Aggregation), a novel model that combines global and local information to effectively solve VRPs. DGL dynamically adjusts local node selections within a localized range, capturing local invariance across problems of different scales and distributions, thereby enhancing generalization. At the same time, DGL integrates global context into the decision-making process, providing richer information for more informed decisions. Additionally, we propose a replacement-based self-improvement learning framework that leverages data augmentation and random replacement techniques, further enhancing DGL's robustness. Extensive experiments on synthetic datasets, benchmark datasets, and real-world country map instances demonstrate that DGL achieves state-of-the-art performance, particularly in generalizing to large-scale VRPs and real-world scenarios. These results showcase DGL's effectiveness in solving complex, realistic optimization challenges and highlight its potential for practical applications.