Acquiring fine-grained object detection annotations in unconstrained images is time-consuming, expensive, and prone to noise, especially in crowdsourcing scenarios. Most prior object detection methods assume accurate annotations; A few recent works have studied object detection with noisy crowdsourced annotations, with evaluation on distinct synthetic crowdsourced datasets of varying setups under artificial assumptions. To address these algorithmic limitations and evaluation inconsistency, we first propose a novel Bayesian Detector Combination (BDC) framework to more effectively train object detectors with noisy crowdsourced annotations, with the unique ability of automatically inferring the annotators' label qualities. Unlike previous approaches, BDC is model-agnostic, requires no prior knowledge of the annotators' skill level, and seamlessly integrates with existing object detection models. Due to the scarcity of real-world crowdsourced datasets, we introduce large synthetic datasets by simulating varying crowdsourcing scenarios. This allows consistent evaluation of different models at scale. Extensive experiments on both real and synthetic crowdsourced datasets show that BDC outperforms existing state-of-the-art methods, demonstrating its superiority in leveraging crowdsourced data for object detection.
论文检索
输入标题、作者或关键词，从 901 篇学术成果中精准定位
Multiple instance learning (MIL) has been extensively applied to whole slide histopathology image (WSI) analysis. The existing aggregation strategy in MIL, which primarily relies on the first-order distance (e.g., mean difference) between instances, fails to accurately approximate the true feature distribution of each instance, leading to biased slide-level representations. Moreover, the scarcity of WSI observations easily leads to model overfitting, resulting in unstable testing performance and limited generalizability. To tackle these challenges, we propose a new Bayesian nonparametric framework for multiple instance learning, which adopts a cascade of Dirichlet processes (cDP) to incorporate the instance-to-bag characteristic of the WSIs. We perform feature aggregation based on the latent clusters formed by the Dirichlet process, which incorporates the covariances of the patch features and forms more representative clusters. We then perform bag-level prediction with another Dirichlet process model on the bags, which imposes a natural regularization on learning to prevent overfitting and enhance generalizability. Moreover, as a Bayesian nonparametric method, the cDP model can accurately generate posterior uncertainty, which allows for the detection of outlier samples and tumor localization. Extensive experiments on five WSI benchmarks validate the superior performance of our method, as well as its generalizability and ability to estimate uncertainties. Codes are anonymously available at https://anonymous.4open.science/r/cDPMIL-F130.
Online action detection aims at identifying the ongoing action in a streaming video without seeing the future. Timely and reliable response is critical for real-world applications. In this paper, we introduce Bayesian Evidential Deep Learning (BEDL), an efficient and generalizable framework for online action detection and uncertainty quantification. Specifically, we combine Bayesian neural networks and evidential deep learning by a teacher-student architecture. The teacher model is built in a Bayesian manner and transfers its mutual information and distribution to the student model through evidential deep learning. In this way, the student model can make accurate online inference while efficiently quantifying the uncertainty. Compared to existing evidential deep learning methods, BEDL estimates uncertainty more accurately by leveraging the Bayesian teacher model. In addition, we designed an attention module for BEDL that can select important features based on the Bayesian mutual information for online inference. We evaluated BEDL on benchmark datasets including THUMPS'14, TVSeries, and HDD. BEDL achieves competitive performance while keeping efficient inference. Extensive ablation studies demonstrate the effectiveness of each component. And the uncertainty quantification is verified by experiments of online anomaly detection using the student model.
Perceptual-Distortion Balanced Image Super-Resolution is a Multi-Objective Optimization Problem
PDF ↗In this paper, we introduce a novel approach to single-image super-resolution (SISR) that balances perceptual quality and distortion through multi-objective optimization (MOO). Traditional pixel-based distortion metrics like PSNR and SSIM often fail to align with human perceptual quality, resulting in blurry outputs despite high scores. To address this, we propose the Multi-Objective Bayesian Optimization Super-Resolution (MOBOSR) framework, which dynamically adjusts loss weights during training. This reduces the need for manual hyperparameter tuning and lessens computational demands compared to AutoML. Our method conceptualizes the relationship between loss weights and image quality assessment (IQA) metrics as black-box objective functions, optimized to achieve an optimal perception-distortion Pareto frontier. Extensive experiments demonstrate that MOBOSR surpasses current state-of-the-art methods in both perception and distortion, significantly advancing the perception-distortion Pareto frontier. Our work lays a foundation for future exploration of the balance between perceptual quality and fidelity in image restoration tasks. Source codes and pretrained models are available at: https://github.com/ZhuKeven/MOBOSR.
The posterior estimation of parameters based on Bayesian theory is a crucial technique in Incremental Learning (IL). The estimated posterior is typically utilized to impose loss regularization, which aligns the current training model parameters with the previously learned posterior to mitigate catastrophic forgetting, a major challenge in IL. However, this additional loss regularization can also impose detriment to the model learning, preventing it from reaching the true global optimum. To overcome this limitation, this paper introduces a novel Bayesian IL framework, Robust Parameter Posterior Fusion (RP2F). Unlike traditional methods, RP2F directly estimates the parameter posterior for new data without introducing extra loss regularization, which allows the model to accommodate new knowledge more sufficiently. It then fuses this new posterior with the existing ones based on the Maximum A Posteriori (MAP) principle, ensuring effective knowledge sharing across tasks. Furthermore, RP2F incorporates a common parameter-robustness priori to facilitate a seamless integration during posterior fusion. Comprehensive experiments on CIFAR-10, CIFAR-100, and Tiny-ImageNet datasets show that RP2F not only effectively mitigates catastrophic forgetting but also achieves backward knowledge transfer.
In an era dominated by web-based intelligent customer services, the applications of Sentence Pair Matching are profoundly broad. Web agents, for example, automatically respond to customer queries by finding similar past questions, significantly reducing customer service expenses. While current large language models (LLMs) offer powerful text generation capabilities, they often struggle with opacity, potential text toxicity, and difficulty managing domain-specific and confidential business inquiries. Consequently, the widespread adoption of web-based intelligent customer services in real-world business still greatly relies on query-based interactions. In this paper, we introduce a series of model-agnostic techniques aimed at enhancing both the accuracy and interpretability of Chinese pairwise sentence-matching models. Our contributions include (1) An Edit-distance-weighted fine-tuning method, (2) A Bayesian Iterative Prediction algorithm, (3) A Lexical-based Dual Ranking Interpreter, and (4) A Bi-criteria Denoising strategy. Experimental results on the Large-scale Chinese Question Matching Corpus (LCQMC) with a disturbed test demonstrate that our fine-tuning and prediction methods can steadily improve matching accuracy, building on the current state-of-the-art models. Besides, our interpreter with denoising strategy markedly enhances token-level interpretation in rationality and loyalty. In both matching accuracy and interpretation, our approaches outperform classic methods and even LLMs.
Recently, how the model performance scales with the training sample size has been extensively studied for large models on vision and language related domains. Nevertheless, the ubiquitous node classification tasks on web-scale graphs were ignored, where the traits of these tasks, such as non-IIDness and transductive setting, are likely to cause different scaling laws and motivate novel techniques to beat the law. Therefore, we first explore the neural scaling law for node classification tasks on three large-scale graphs. Then, we benchmark several state-of-the-art data pruning methods on these tasks, not only validating the possibility of improving the original unsatisfactory power law but also gaining insights into a hard-and-representative principle on picking an effective subset of training nodes. Moreover, we leverage the transductive setting to propose a novel data pruning method, which instantiates our principle in a test set-targeted manner. Our method consistently outperforms related methods on all three datasets. Meanwhile, we utilize a PAC-Bayesian framework to analyze our method, extending prior results to account for both hardness and representativeness. In addition to a promising way to ease GNN training on web-scale graphs, our study offers knowledge of the relationship between training nodes and GNN generalization.
In today's online advertising markets, it is common for advertisers to set long-term budgets. Correspondingly, advertising platforms adopt budget control methods to ensure that advertisers' payments lie within their budgets. Most budget control methods rely on the value distributions of advertisers. However, due to the complex advertising landscape and potential privacy concerns, the platform hardly learns advertisers' true priors. Thus, it is crucial to understand how budget control auction mechanisms perform under unassured priors. This work answers this problem from multiple aspects. Specifically, we examine five budget-constrained parameterized mechanisms: bid-discount/pacing first-price/second-price auctions and the Bayesian revenue-optimal auction. We consider the unassured prior game among the seller and all buyers induced by these five mechanisms in the stochastic model. We restrict the parameterized mechanisms to satisfy the budget-extracting condition, which maximizes the seller's revenue by extracting buyers' budgets as effectively as possible. Our main result shows that the Bayesian revenue-optimal mechanism and the budget-extracting bid-discount first-price mechanism yield the same set of Nash equilibrium outcomes in the unassured prior game. This implies that simple mechanisms can be as robust as the optimal mechanism under unassured priors in the budget-constrained setting. In the symmetric case, we further show that all these five (budget-extracting) mechanisms share the same set of possible outcomes. We further dig into the structural properties of these mechanisms. We characterize sufficient and necessary conditions on the budget-extracting parameter tuple for bid-discount/pacing first-price auctions. Meanwhile, when buyers do not take strategic behaviors, we exploit the dominance relationships of these mechanisms by revealing their intrinsic structures. In summary, our results establish vast connections among budget-constrained auctions with unassured priors and explore their structural properties, particularly highlighting the advantages of first-price mechanisms.
An Offline Meta Black-box Optimization Framework for Adaptive Design of Urban Traffic Light Management Systems
PDF ↗Complex urban road networks with high vehicle occupancy frequently face severe traffic congestion. Designing an effective strategy for managing multiple traffic lights plays a crucial role in managing congestion. However, most current traffic light management systems rely on human-crafted decisions, which may not adapt well to diverse traffic patterns. In this paper, we delve into two pivotal design components of the traffic light management system that can be dynamically adjusted to various traffic conditions: phase combination and phase time allocation. While numerous studies have sought an efficient strategy for managing traffic lights, most of these approaches consider a fixed traffic pattern and are limited to relatively small road networks. To overcome these limitations, we introduce a novel and practical framework to formulate the optimization of such design components using an offline meta black-box optimization. We then present a simple yet effective method to efficiently find a solution for the aforementioned problem. In our framework, we first collect an offline meta dataset consisting of pairs of design choices and corresponding congestion measures from various traffic patterns. After collecting the dataset, we employ the Attentive Neural Process (ANP) to predict the impact of the proposed design on congestion across various traffic patterns with well-calibrated uncertainty. Finally, Bayesian optimization, with ANP as a surrogate model, is utilized to find an optimal design for unseen traffic patterns through limited online simulations. Our experiment results show that our method outperforms state-of-the-art baselines on complex road networks in terms of the number of waiting vehicles. Surprisingly, the deployment of our method into a real-world traffic system was able to improve traffic throughput by 4.80% compared to the original strategy.
Predicting click-through rate (CTR) is a critical task in recommendation systems, where the models are optimized with pointwise loss to infer the probability of items being clicked. In industrial practice, applications also require ranking items based on these probabilities. Existing solutions primarily combine the ranking-based loss, i.e., pairwise and listwise loss, with CTR prediction. However, they can hardly calibrate or generalize well in CTR scenarios where the clicks reflect the binary preference. This is because the binary click feedback leads to a large number of ties, which renders high data sparsity. In this paper, we propose an effective data augmentation strategy, named Beyond Binary Preference (BBP) training framework, to address this problem. Our key idea is to break the ties by leveraging Bayesian approaches, where the beta distribution models click behavior as probability distributions in the training data that naturally break ties. Therefore, we can obtain an auxiliary training label that generates more comparable pairs and improves the ranking performance. Besides, BBP formulates ranking and calibration as a multi-task framework to optimize both objectives simultaneously. Through extensive offline experiments and online tests on various datasets, we demonstrate that BBP significantly outperforms state-of-the-art methods in both ranking and calibration capabilities, showcasing its effectiveness in addressing the limitations of existing methods. Our code is available at https://github.com/AlvinIsonomia/BBP.
Source localization aims to locate information diffusion sources only given the diffusion observation, which has attracted extensive attention in the past few years. Existing methods are mostly tailored for single networks and may not be generalized to handle more complex networks like cross-networks. Cross-network is defined as two interconnected networks, where one network's functionality depends on the other. Source localization on cross-networks entails locating diffusion sources on the source network by only giving the diffused observation in the target network. The task is challenging due to challenges including: 1) diffusion sources distribution modeling; 2) jointly considering both static and dynamic node features; and 3) heterogeneous diffusion patterns learning. In this work, we propose a novel method, namely CNSL, to handle the three primary challenges. Specifically, we propose to learn the distribution of diffusion sources through Bayesian inference and leverage disentangled encoders to learn static and dynamic node features separately. The learning objective is coupled with the cross-network information propagation estimation model to make the inference of diffusion sources considering the overall diffusion process. Additionally, we also provide two novel cross-network datasets collected by ourselves. Extensive experiments are conducted on both datasets to demonstrate the effectiveness of CNSL in handling the source localization on cross-networks.
With breakthroughs in pretrained language models, a large number of finetuned models specialized in distinct domains have surfaced online. Yet, when faced with a fresh dataset covering multiple (sub)domains, their performance might degrade. Reusing these available finetuned models to train a new model is a more feasible solution than the finetuning method that demands extensive manual labeling. Knowledge Amalgamation (KA) is such a model reusing technique, which derives a new model (termed student model) by amalgamating those trained models (termed teacher models) tailored for distinct domains, bypassing the need for manual labeling. However, when the domains of text samples are unknown, selecting a number of appropriate teacher models (simply called a combination) for reuse becomes complicated. To learn an accurate student model, the classical KA method resorts to manual selections, a process both tedious and inefficient. Our study pioneers the automation of this combination selection process for KA in the fundamental text classification task, an area previously unexplored. In this paper, we introduce BoKA : an automatic knowledge amalgamation framework for identifying a combination that can learn a superior student model without human labor. Through the lens of Bayesian optimization, BoKA iteratively samples a subset of possible combinations for amalgamation instead of manual selections. Furthermore, we introduce a novel KA method tailored for text classification, which guides the student model using both soft and pseudo-hard labels from the teacher models when their predictions are closely aligned; in cases of significant disagreement, it uses randomly generated labels. Experiments on two public multi-domain datasets show that BoKA achieves remarkable efficiency by sampling only up to 5.5% of all potential combinations. Moreover, BoKA is capable of matching or even surpassing leading zero-shot large language models, despite having dozens of times fewer parameters.
Sum-product networks (SPNs) are probabilistic models characterized by exact and fast evaluation of fundamental probabilistic operations. Its superior computational tractability has led to applications in many fields, such as machine learning with time constraints or accuracy requirements and real-time systems. The structural constraints of SPNs supporting fast inference, however, lead to increased learning-time complexity and can be an obstacle to building highly expressive SPNs. This study aimed to develop a Bayesian learning approach that can be efficiently implemented on large-scale SPNs. We derived a new full conditional probability of Gibbs sampling by marginalizing multiple random variables to expeditiously obtain the posterior distribution. The complexity analysis revealed that our sampling algorithm works efficiently even for the largest possible SPN. Furthermore, we proposed a hyperparameter tuning method that balances the diversity of the prior distribution and optimization efficiency in large-scale SPNs. Our method has improved learning-time complexity and demonstrated computational speed tens to more than one hundred times faster and superior predictive performance in numerical experiments on more than 20 datasets.
The Combined Algorithm Selection and Hyperparameter Optimization (CASH) problem is pivotal in Automatic Machine Learning (AutoML). Most leading approaches combine Bayesian optimization with post-hoc ensemble building to create advanced AutoML systems. Bayesian optimization (BO) typically focuses on identifying a singular algorithm and its hyperparameters that outperform all other configurations. Recent developments have highlighted an oversight in prior CASH methods: the lack of consideration for diversity among the base learners of the ensemble. This oversight was overcome by explicitly injecting the search for diversity into the traditional CASH problem. However, despite recent developments, BO's limitation lies in its inability to directly optimize ensemble generalization error, offering no theoretical assurance that increased diversity correlates with enhanced ensemble performance. Our research addresses this gap by establishing a theoretical foundation that integrates diversity into the core of BO for direct ensemble learning. We explore a theoretically sound framework that describes the relationship between pair-wise diversity and ensemble performance, which allows our Bayesian optimization framework Optimal Diversity Bayesian Optimization (OptDivBO) to directly and efficiently minimize ensemble generalization error. OptDivBO guarantees an optimal balance between pairwise diversity and individual model performance, setting a new precedent in ensemble learning within CASH. Empirical results on 20 public datasets show that OptDivBO achieves the best average test ranks of 1.57 and 1.4 in classification and regression tasks.
Prompt learning has gained popularity as a means to leverage the knowledge embedded in pre-trained language models (PLMs) for NLP tasks while using a limited number of trainable parameters. While it has shown promise in tasks like sentiment classification and natural language inference, generating suitable prompts for PLMs, as opposed to human prompts, remains a challenge. In this paper, we introduce an abstraction of the prompt learning process using an extended Kalman filter. Our approach, called Conditional Extended Kalman Filter based on Neural Networks (CEKFNN), effectively infers more appropriate prompt tokens by enhancing the classic extended Kalman filter with PLM's contextual representation power. Specifically, CEKFNN learns transition and emission functions from PLM embeddings of input sentences to infer latent prompt tokens. We refine CEKFNN using an alternate-training approach, retraining a PLM's emission function with prompt tokens inferred by prompt models (PMs), as well as the initial and transition functions. PLM's output labels assist in PMs' training. When updating the pre-trained language model (PLM), we use an adapter approach with few trainable parameters, leaving PLM parameters frozen. We evaluate CEKFNN across open-source PLMs, demonstrating performance improvements over state-of-the-art methods while using a limited number of trainable parameters. It shows that CEKFNN performs on-par or better than fine-tuning, which requires updating all parameters in the PLM.
Negative-Binomial Randomized Gamma Dynamical Systems for Heterogeneous Overdispersed Count Time Sequences
PDF ↗Modeling count-valued time sequences has been receiving growing interests because count time sequences naturally arise in physical and social domains. Poisson gamma dynamical systems (PGDSs) are newly-developed methods, which can well capture the expressive latent transition structure and bursty dynamics behind count sequences. In particular, PGDSs demonstrate superior performance in terms of data imputation and prediction, compared with canonical linear dynamical system (LDS) based methods. Despite these advantages, PGDS cannot capture the heterogeneous overdispersed behaviours of the underlying dynamic processes. To mitigate this defect, we propose a negative-binomial-randomized gamma Markov process, which not only significantly improves the predictive performance of the proposed dynamical system, but also facilitates the fast convergence of the inference algorithm. Moreover, we develop methods to estimate both factor-structured and graph-structured transition dynamics, which enable us to infer more explainable latent structure, compared with PGDSs. Finally, we demonstrate the explainable latent structure learned by the proposed method, and show its superior performance in imputing missing data and forecasting future observations, compared with the related models.
Robotics and automation offer massive acceleration for solving intractable, multivariate scientific problems such as materials discovery, but the available search spaces can be dauntingly large. Bayesian optimization has emerged as a popular sample-efficient optimization engine, thriving in tasks where no analytic form of the target function/property is known. Here, we exploit expert human knowledge in the form of hypotheses to direct Bayesian searches more quickly to promising regions of chemical space. Previous methods have used underlying distributions derived from existing experimental measurements, which is unfeasible for new, unexplored scientific tasks. Also, such distributions cannot capture intricate hypotheses. Our proposed method uses expert human hypotheses to generate improved seed samples. Unpromising seeds are automatically discounted, while promising seeds are used to augment the surrogate model data, thus achieving better-informed sampling. This process continues in a global versus local search fashion, organized in a bilevel optimization framework. We validate the performance of our method on a range of synthetic functions and demonstrate its practical utility on a real chemical design task where the use of expert hypotheses accelerates the search performance significantly.
In recommender systems, preference elicitation (PE) is an effective way to learn about a user's preferences to improve recommendation quality. Expected value of information (EVOI), a Bayesian technique that computes expected gain in user utility, has proven to be effective in selecting useful PE queries. Most EVOI methods use probabilistic models of user preferences and query responses to compute posterior utilities. By contrast, we develop model-free variants of EVOI that rely on function approximation to obviate the need for specific modeling assumptions. Specifically, we learn user response and utility models from existing data (often available in real-world recommender systems), which are used to estimate EVOI rather than relying on explicit probabilistic inference. We augment our approach by using online planning, specifically, Monte Carlo tree search, to further enhance our elicitation policies. We show that our approach offers significant improvement in recommendation quality over standard baselines on several PE tasks.
VSGT: Variational Spatial and Gaussian Temporal Graph Models for EEG-based Emotion Recognition
PDF ↗Electroencephalogram (EEG), which directly reflects the emotional activity of the brain, has been increasingly utilized for emotion recognition. Most works exploit the spatial and temporal dependencies in EEG to learn emotional feature representations, but they still have two limitations to reach their full potential. First, prior knowledge is rarely used to capture the spatial dependency of brain regions. Second, the cross temporal dependency between consecutive time slices for different brain regions is ignored. To address these limitations, in this paper, we propose Variational Spatial and Gaussian Temporal (VSGT) graph models to investigate the spatial and temporal dependencies for EEG-based emotion recognition. The VSGT has two key components: Variational Spatial Encoder (VSE) and Gaussian Temporal Encoder (GTE). The VSE leverages the upper bound theorem to identify the dynamic spatial dependency based on prior knowledge by the variational Bayesian method. Besides, the GTE exploits the conditional Gaussian graph transform that computes comprehensive temporal dependency between consecutive time slices. Finally, the VSGT utilizes a recurrent structure to calculate the spatial and temporal dependencies for all time slices. Extensive experiments show the superiority of VSGT over state-of-the-art methods on multiple EEG datasets.
Estimating before Debiasing: A Bayesian Approach to Detaching Prior Bias in Federated Semi-Supervised Learning
PDF ↗Federated Semi-Supervised Learning (FSSL) leverages both labeled and unlabeled data on clients to collaboratively train a model. In FSSL, the heterogeneous data can introduce prediction bias into the model, causing the model's prediction to skew towards some certain classes. Existing FSSL methods primarily tackle this issue by enhancing consistency in model parameters or outputs. However, as the models themselves are biased, merely constraining their consistency is not sufficient to alleviate prediction bias. In this paper, we explore this bias from a Bayesian perspective and demonstrate that it principally originates from label prior bias within the training data. Building upon this insight, we propose a debiasing method for FSSL named FedDB. FedDB utilizes the Average Prediction Probability of Unlabeled Data (APP-U) to approximate the biased prior. During local training, FedDB employs APP-U to refine pseudo-labeling through Bayes' theorem, thereby significantly reducing the label prior bias. Concurrently, during the model aggregation, FedDB uses APP-U from participating clients to formulate unbiased aggregate weights, thereby effectively diminishing bias in the global model. Experimental results show that FedDB can surpass existing FSSL methods. The code is available at https://github.com/GuogangZhu/FedDB.