论文检索

Kaize Ding, Xiaoxiao Ma 0002, Yixin Liu 0001, Shirui Pan

Graph neural networks (GNNs) based on message passing have achieved remarkable performance in graph machine learning. By combining it with the power of pseudo labeling, one can further push forward the performance on the task of semi-supervised node classification. However, most existing works assume that the training node labels are purely noise-free, while this strong assumption usually does not hold in practice. GNNs will overfit the noisy training labels and the adverse effects of mislabeled nodes can be exaggerated by being propagated to the remaining nodes through the graph structure, exacerbating the model failure. Worse still, the noisy pseudo labels could also largely undermine the model's reliability without special treatment. In this paper, we revisit the role of (1) message passing and (2) pseudo labels in the studied problem and try to address two denoising subproblems from the model architecture and algorithm perspective, respectively. Specifically, we first develop a label-noise robust GNN that discards the coupled message-passing scheme. Despite its simple architecture, this learning backbone prevents overfitting to noisy labels and also inherently avoids the noise propagation issue. Moreover, we propose a novel reliable graph pseudo labeling algorithm that can effectively leverage the knowledge of unlabeled nodes while mitigating the adverse effects of noisy pseudo labels. Based on those novel designs, we can attain exceptional effectiveness and efficiency in solving the studied problem. We conduct extensive experiments on benchmark datasets for semi-supervised node classification with different levels of label noise and show new state-of-the-art performance. The code is available at https://github.com/DND-NET/DND-NET.

Siddhartha Shankar Das, S. M. Ferdous, Mahantesh M. Halappanavar, Edoardo Serra, Alex Pothen

We propose AGS-GNN, a novel attribute-guided sampling algorithm for Graph Neural Networks (GNNs). AGS-GNN exploits the node features and the connectivity structure of a graph while simultaneously adapting for both homophily and heterophily in graphs. In homophilic graphs, vertices of the same class are more likely to be adjacent, but vertices of different classes tend to be adjacent in heterophilic graphs. GNNs have been successfully applied to homophilic graphs, but their utility to heterophilic graphs remains challenging. The state-of-the-art GNNs for heterophilic graphs use the full neighborhood of a node instead of sampling it, and hence do not scale to large graphs and are not inductive. We develop dual-channel sampling techniques based on feature-similarity and feature-diversity to select subsets of neighbors for a node that capture adaptive information from homophilic and heterophilic neighborhoods. Currently, AGS-GNN is the only algorithm that explicitly controls homophily in the sampled subgraph through similar and diverse neighborhood samples. For diverse neighborhood sampling, we employ submodularity, a novel contribution in this context. We pre-compute the sampling distribution in parallel, achieving the desired scalability. Using an extensive dataset consisting of 35 small (< 100K nodes) and large (- 100K nodes) homophilic and heterophilic graphs, we demonstrate the superiority of AGS-GNN compared to the state-of-the-art approaches. AGS-GNN achieves test accuracy comparable to the best-performing heterophilic GNNs, even outperforming methods that use the entire graph for node classification. AGS-GNN converges faster than methods that sample neighborhoods randomly, and can be incorporated into existing GNN models that employ node or graph sampling.

In-Koo Cho, Jonathan A. Libgober, Cheng Ding

We propose an efficient boosting algorithm for multiclass classification, called AdaBoost.Iter, that extends SAMME and AdaBoost. The algorithm iteratively applies the weak learnability condition of SAMME to eliminate classes to find the correct classificiation. The iterative weak learnability is a sufficient and necessary condition for boostability, but it is also easier to validate than the EOR criterion of AdaBoost.MM \citeMukherjeeSchapire2013. We show that the training error of AdaBoost.Iter vanishes at the exponential rate, while the generalization error converges to zero at the same rate as AdaBoost. AdaBoost.Iter numerically outperforms SAMME and achieves performance comparable to AdaBoost.MM on benchmark datasets.

Yao Cheng 0009, Caihua Shan, Yifei Shen 0004, Xiang Li 0067, Siqiang Luo, Dongsheng Li 0002

Label noise is a common challenge in large datasets, as it can significantly degrade the generalization ability of deep neural networks. Most existing studies focus on noisy labels in computer vision; however, graph models encompass both node features and graph topology as input, and become more susceptible to label noise through message-passing mechanisms. Recently, only a few works have been proposed to tackle the label noise on graphs. One significant limitation is that they operate under the assumption that the graph exhibits homophily and that the labels are distributed smoothly. However, real-world graphs can exhibit varying degrees of heterophily, or even be dominated by heterophily, which results in the inadequacy of the current methods. In this paper, we study graph label noise in the context of arbitrary heterophily, with the aim of rectifying noisy labels and assigning labels to previously unlabeled nodes. We begin by conducting two empirical analyses to explore the impact of graph homophily on graph label noise. Following observations, we propose a efficient algorithm, denoted as R2LP. Specifically, R2LP is an iterative algorithm with three steps: (1) reconstruct the graph to recover the homophily property, (2) utilize label propagation to rectify the noisy labels, (3) select high-confidence labels to retain for the next iteration. By iterating these steps, we obtain a set of ''correct'' labels, ultimately achieving high accuracy in the node classification task. The theoretical analysis is also provided to demonstrate its remarkable denoising effect. Finally, we perform experiments on ten benchmark datasets with different levels of graph heterophily and various types of noise. In these experiments, we compare the performance of R2LP against ten typical baseline methods. Our results illustrate the superior performance of the proposed øurs. The code and data of this paper can be accessed at: https://github.com/cy623/R2LP.git.

Lin Chen 0002, Fengli Xu, Nian Li 0001, Zhenyu Han, Meng Wang 0001, Yong Li 0008, Pan Hui 0001

Heterogeneous information networks (HIN) have gained increasing popularity in recent years for capturing complex relations between diverse types of nodes. Meta-structures are proposed as a useful tool to identify the important patterns in HINs, but hand-crafted meta-structures pose significant challenges for scaling up, drawing wide research attention towards developing automatic search algorithms. Previous efforts primarily focused on searching for meta-structures with good empirical performance, overlooking the importance of human comprehensibility and generalizability. To address this challenge, we draw inspiration from the emergent reasoning abilities of large language models (LLMs). We propose ReStruct, a meta-structure search framework that integrates LLM reasoning into the evolutionary procedure. ReStruct uses a grammar translator to encode the meta-structures into natural language sentences, and leverages the reasoning power of LLMs to evaluate their semantic feasibility. Besides, ReStruct also employs performance-oriented evolutionary operations. These two competing forces allow ReStruct to jointly optimize the semantic explainability and empirical performance of meta-structures. Furthermore, ReStruct contains a differential LLM explainer to generate and refine natural language explanations for the discovered meta-structures by reasoning through the search history. Experiments on eight representative HIN datasets demonstrate that ReStruct achieves state-of-the-art performance in both recommendation and node classification tasks. Moreover, a survey study involving 73 graduate students shows that the discovered meta-structures and generated explanations by ReStruct are substantially more comprehensible. Our code and questionnaire are available at https://github.com/LinChen-65/ReStruct.

Shuzhi Cao, Jianfei Ruan, Bo Dong 0001, Bin Shi

In label-noise learning, accurately identifying the transition matrix is crucial for developing statistically consistent classifiers. This task is complicated by instance-dependent noise, which introduces identifiability challenges in the absence of stringent assumptions. Existing methods use neural networks to estimate the transition matrix by initially extracting confident clean instances. However, this extraction process is hindered by severe inter-class imbalance and a bias toward selecting unambiguous intra-class instances, leading to a distorted understanding of noise patterns. To tackle these challenges, our paper introduces a Class Rebalance and Geometric Regularization-based Framework (CRGR). CRGR employs a smoothed, noise-tolerant reweighting mechanism to equilibrate inter-class representation, thereby mitigating the risk of model overfitting to dominant classes. Additionally, recognizing that instances with similar characteristics often exhibit parallel noise patterns, we propose that the transition matrix should mirror the similarity of the feature space. This insight promotes the inclusion of ambiguous instances in training, serving as a form of geometric regularization. Such a strategy enhances the model's ability to navigate diverse noise patterns and strengthens its generalization capabilities. By addressing both inter-class and intra-class biases, CRGR offers a more balanced and robust classification model. Extensive experiments on both synthetic and real-world datasets demonstrate CRGR's superiority over existing state-of-the-art methods, significantly boosting classification accuracy and showcasing its effectiveness in handling instance-dependent noise.

Yikun Ban, Yunzhe Qi, Tianxin Wei, Lihui Liu, Jingrui He

The contextual bandit has been identified as a powerful framework to formulate the recommendation process as a sequential decision-making process, where each item is regarded as an arm and the objective is to minimize the regret of T rounds. In this paper, we study a new problem, Clustering of Neural Bandits, by extending previous work to the arbitrary reward function, to strike a balance between user heterogeneity and user correlations in the recommender system. To solve this problem, we propose a novel algorithm called M-CNB, which utilizes a meta-learner to represent and rapidly adapt to dynamic clusters, along with an informative Upper Confidence Bound (UCB)-based exploration strategy. We provide an instance-dependent performance guarantee for the proposed algorithm that withstands the adversarial context, and we further prove the guarantee is at least as good as state-of-the-art (SOTA) approaches under the same assumptions. In extensive experiments conducted in both recommendation and online classification scenarios, M-CNB outperforms SOTA baselines. This shows the effectiveness of the proposed approach in improving online recommendation and online classification performance.

Minyoung Bae, Yooju Shin, Youngeun Nam, Youngseop Lee, Jae-Gil Lee 0001

Although time-series classification has many applications in healthcare and manufacturing, the high cost of data collection and labeling hinders its widespread use. To reduce data collection and labeling costs while maintaining high classification accuracy, we propose a novel problem setting, called semi-supervised learning with low-sampling-rate time series, in which the majority of time series are collected at a low sampling rate and are unlabeled whereas the minority of time series are collected at a high sampling rate and are labeled. For this novel problem scenario, we develop the SemiTSR framework equipped with the super-resolution module and the semi-supervised learning module. Here, low-sampling-rate time series are upsampled precisely, taking periodicity and trend at each timestamp into account, and both labeled and unlabeled high-sampling-rate time series are utilized for training. In particular, consistency regularization between artificially downsampled time series derived from an original high-sampling-rate time series is effective at overcoming limited sampling rates. We demonstrate that SemiTSR significantly outperforms conventional semi-supervised learning techniques by assuring high classification accuracy with low-sampling-rate time series.

Amitoz Azad, Yuan Fang 0001

Geodesic distances on manifolds have numerous applications in image processing, computer graphics and computer vision. In this work, we introduce an approach called 'LGGD' (Learned Generalized Geodesic Distances). This method involves generating node features by learning a generalized geodesic distance function through a training pipeline that incorporates training data, graph topology and the node content features. The strength of this method lies in the proven robustness of the generalized geodesic distances to noise and outliers. Our contributions encompass improved performance in node classification tasks, competitive results with state-of-the-art methods on real-world graph datasets, the demonstration of the learnability of parameters within the generalized geodesic equation on graph, and dynamic inclusion of new labels.

Tong Zhou, Yubo Chen, Pengfei Cao, Kang Liu, Shengping Liu, Jun Zhao

Data is one of the most critical elements in building a large language model. However, existing systems either fail to customize a corpus curation pipeline or neglect to leverage comprehensive corpus assessment for iterative optimization of the curation. To this end, we present a pretraining corpus curation and assessment platform called Oasis — a one-stop system for data quality improvement and quantification with user-friendly interactive interfaces. Specifically, the interactive modular rule filter module can devise customized rules according to explicit feedback. The debiased neural filter module builds the quality classification dataset in a negative-centric manner to remove the undesired bias. The adaptive document deduplication module could execute large-scale deduplication with limited memory resources. These three parts constitute the customized data curation module. And in the holistic data assessment module, a corpus can be assessed in local and global views, with three evaluation means including human, GPT-4, and heuristic metrics. We exhibit a complete process to use Oasis for the curation and assessment of pretraining data. In addition, an 800GB bilingual corpus curated by Oasis is publicly released.

Shinnosuke Tanaka, James Barry, Vishnudev Kuruvanthodi, Movina Moses, Maxwell J. Giammona, Nathan Herr, Mohab Elkaref, Geeth de Mel

This paper describes the KnowledgeHub tool, a scientific literature Information Extraction (IE) and Question Answering (QA) pipeline. This is achieved by supporting the ingestion of PDF documents that are converted to text and structured representations. An ontology can then be constructed where a user defines the types of entities and relationships they want to capture. A browser-based annotation tool enables annotating the contents of the PDF documents according to the ontology. Named Entity Recognition (NER) and Relation Classification (RC) models can be trained on the resulting annotations and can be used to annotate the unannotated portion of the documents. A knowledge graph is constructed from these entity and relation triples which can be queried to obtain insights from the data. Furthermore, we integrate a suite of Large Language Models (LLMs) that can be used for QA and summarisation that is grounded in the included documents. KnowledgeHub is a unique tool that supports annotation, IE and QA, which gives the user full insight into the knowledge discovery pipeline.

Hung Nguyen, Tobias Clement, Loc Nguyen, Nils Kemmerzell, Binh Truong, Khang Nguyen, Mohamed Abdelaal, Hung Cao

LangXAI is a framework that integrates Explainable Artificial Intelligence (XAI) with advanced vision models to generate textual explanations for visual recognition tasks. Despite XAI advancements, an understanding gap persists for end-users with limited domain knowledge in artificial intelligence and computer vision. LangXAI addresses this by furnishing text-based explanations for classification, object detection, and semantic segmentation model outputs to end-users. Preliminary results demonstrate LangXAI's enhanced plausibility, with high BERTScore across tasks, fostering a more transparent and reliable AI framework on vision tasks for end-users. The code and demo of this work can be found at https://analytics-everywhere-lab.github.io/langxai.io/.

Hamit Kavas, Marc Serra-Vidal, Leo Wanner

In the context of the increasingly globalised economy and labour market, recruitment agencies face the challenge to deal with a magnitude of job offers and job applications written in a variety of languages, formats, and styles. Quite often, this leads to a suboptimal evaluation of the CVs of job seekers with respect to their relevance to a job offer. To address this challenge, we propose an interactive system that follows the ``human-in-the-loop'' approach, actively involving recruiters in the job offer -- applicant CV matching. The system uses a fine-tuned state-of-the-art classification model that aligns job seeker CVs with labels of the {\it European Skills, Competences, Qualifications and Occupations} taxonomy to propose an initial match between job offers with the CVs of job candidates. This match is refined in sequential LLM driven-interaction with the recruiter, which culminates in CV relevance scores and reports that justify them.

Hannes Kath, Patricia P. Serafini, Ivan B. Campos, Thiago S. Gouvêa, Daniel Sonntag

Passive Acoustic Monitoring (PAM) has become a key technology in wildlife monitoring, generating large amounts of acoustic data. However, the effective application of machine learning methods for sound event detection in PAM datasets is highly dependent on the accessibility of annotated data, a process that can be labour intensive. As a team of domain experts and machine learning researchers, in this paper we present a no-code annotation tool designed for PAM datasets that incorporates transfer learning and active learning strategies to address the data annotation challenge inherent in PAM. Transfer learning is applied to use pre-trained models to compute meaningful embeddings from the PAM audio files. Active learning iteratively identifies the most informative samples and then presents them to the user for annotation. This iterative approach improves the performance of the model compared to random sample selection. In a preliminary evaluation of the tool, a domain expert annotated part of a real PAM data set. Compared to conventional tools, the workflow of the proposed tool showed a speed improvement of 2-4 times. Further enhancements, such as the incorporation of sound examples, have the potential to further improve efficiency.

Jonathan Erskine, Matt Clifford, Alexander Hepburn, Raul Santos Rodriguez

Human-Computer Interaction has been shown to lead to improvements in machine learning systems by boosting model performance, accelerating learning and building user confidence. In this work, we aim to alleviate the expectation that human annotators adapt to the constraints imposed by traditional labels by allowing for extra flexibility in the form that supervision information is collected. For this, we propose a human-machine learning interface for binary classification tasks which enables human annotators to utilise counterfactual examples to complement standard binary labels as annotations for a dataset. Finally we discuss the challenges in future extensions of this work.

Kartik Chari, Niklas Kueper, Su Kyoung Kim, Frank Kirchner, Elsa Andrea Kirchner

Reliable detection of human intentions from electroencephalogram (EEG) to improve human-robot interaction (HRI) has recently gained significant importance. To ensure safe and satisfactory interactions, implicit detection of erroneous behavior of robotic systems, particularly assistive devices, is essential. This can be achieved by detecting error-related potentials (ErrPs) in EEG, evoked by visual, tactile, or visuo-tactile stimuli. Of these, the ErrPs evoked tactilely with the help of a robot remains unexplored and has been the main focus of this competition. The task for participating teams was to develop robust AI models for continuous real-time classification of erroneous behavior of assistive robotic devices from the human EEG. Even though the competition results prove its feasibility, a performance gap (balanced accuracy and computation time) of more than 10% was observed between the offline and online classification of errors in real-world scenarios. In addition to the competitive AI models developed by the participating teams, this competition also contributed towards a one-of-its-kind open-access EEG and EMG dataset, a lossless live streaming solution for EEG data, and a novel quantitative metric for benchmarking online asynchronous EEG detection solutions.

Gilles Audemard, Jean-Marie Lagniez, Pierre Marquis, Nicolas Szczepanski

PyXAI (Python eXplainable AI) is a Python library designed for providing explanations and cor- recting tree-based Machine Learning (ML) models. It is suited to decision trees, random forests, and boosted trees, when used for regression or classification tasks. In contrast to many model-agnostic approaches to XAI, PyXAI exploits the model it- self to generate explanations, ensuring them to be faithful. PyXAI includes several algorithms for the generation of explanations, which can be abductive or contrastive. PyXAI also includes algorithms for correcting tree-based models when their predictions conflict with pieces of user knowledge.

Mohit Kumar, Bernhard A. Moser, Lukas Fischer

Privacy-utility tradeoff remains as one of the fundamental issues of differentially private machine learning. This paper introduces a geometrically inspired kernel-based approach to mitigate the accuracy-loss issue in classification. In this approach, a representation of the affine hull of given data points is learned in Reproducing Kernel Hilbert Spaces (RKHS). This leads to a novel distance measure that hides privacy-sensitive information about individual data points and improves the privacy-utility tradeoff via significantly reducing the risk of membership inference attacks. The effectiveness of the approach is demonstrated through experiments on MNIST dataset, Freiburg groceries dataset, and a real biomedical dataset. It is verified that the approach remains computationally practical. The application of the approach to federated learning is considered and it is observed that the accuracy-loss due to data being distributed is either marginal or not significantly high.

Aleksandr V. Petrov, Craig Macdonald

Sequential recommendation models predict the next item in a sequence of user-item interactions, akin to how language models predict the next tokens. These models often adapt language model architectures, treating item IDs as if they were token IDs. However, the number of potential items in recommender systems makes calculating the interaction probability for all items impractical during training; therefore, recommender systems frequently employ negative sampling, where the model learns to differentiate between actual user interactions (positives) and randomly chosen non-interactions (negatives), often using Binary Cross-Entropy (BCE) the loss, framing the problem as a binary classification task. We demonstrate that using negative sampling with BCE can lead to overconfidence, where the model's predicted probabilities for user interactions are higher than the actual probabilities. Although the actual score magnitude is not important for ranking items (only the order of scores matters), overconfidence leads to training instability when using Binary Cross-Entropy (BCE) loss. We show that overconfidence explains the performance gap between two leading sequential recommendation models, SASRec and BERT4Rec -- the former uses negative sampling, while the latter does not. To counter overconfidence, we introduce Generalised Binary Cross-Entropy (gBCE) loss and the gSASRec model that utilises gBCE. We mathematically prove and empirically validate that gSASRec effectively addresses the issue of overconfidence. Consequently, gSASRec's effectiveness is better than that of SASRec and matches the state of the BERT4Rec while retaining negative sampling. On the Gowalla dataset with more than 1MM items, where training BERT4Rec is infeasible, gSASRec outperforms the original SASRec model by 41% in terms of NDCG@10.

Najeeb Moharram Jebreel, Josep Domingo-Ferrer, Yiming Li

Training deep neural networks (DNNs) usually requires massive training data and computational resources. Users who cannot afford this may prefer to outsource training to a third party or resort to publicly available pre-trained models. Unfortunately, doing so facilitates a new training-time attack (i.e., backdoor attack) against DNNs. This attack aims to induce misclassification of input samples containing adversary-specified trigger patterns. In this paper, we first conduct a layer-wise feature analysis of poisoned and benign samples from the target class. We find out that the feature difference between benign and poisoned samples tends to be maximum at a critical layer, which is not always the one typically used in existing defenses, namely the layer before fully-connected layers. We also demonstrate how to locate this critical layer based on the behaviors of benign samples. We then propose a simple yet effective method to filter poisoned samples by analyzing the feature differences between suspicious and benign samples at the critical layer. Extensive experiments on two benchmark datasets are reported which confirm the effectiveness of our defense.