Author name cluster
Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.
YNIMG Journal 2026 Journal Article
AAAI Conference 2026 Conference Paper
Sequential recommendation aims to predict the next item based on historical interactions. To further enhance the reasoning capability in sequential recommendation, LLMs are employed to predict the next item or generate semantic IDs for item representation, given LLMs' extensive domain knowledge and reasoning ability. However, existing LLM-based methods suffer from two limitations. (i) The scarcity of recommendation data with reasoning paths makes it challenging to design suitable chain-of-thought prompting templates, and the full potential of LLMs' reasoning abilities remains underutilized. (ii) Upon obtaining semantic IDs, the LLMs and their representations are excluded from the subsequent recommendation model training, preventing downstream models from fully utilizing the rich semantic information encoded within these IDs. To address these issues, we propose a novel CoderRec framework, which is capable of fully exploiting the information encoded in semantic IDs to guide the recommendation process. Specifically, to address the problem of scarcity in reasoning path-augmented data, we introduce latent reasoning into sequential recommendation and treat the representation captured by the downstream model as domain-specific latent thought, enabling implicit logical inference without requiring explicit CoT annotations. To ensure that the downstream recommendation models are able to deeply leverage the semantic information within IDs, we propose a novel cross-scale model collaboration strategy, which employs cross-scale IDs and a two-phase approach to align LLM-derived semantics with recommendation objectives. Extensive experiments have shown the effectiveness of our proposed CoderRec framework.
AAAI Conference 2026 Conference Paper
Mixture-of-Experts (MoE) architectures decouple model capacity from per-token computation, enabling scaling beyond the computational limits imposed by dense scaling laws. Yet how MoE architectures shape knowledge acquisition during pre-training—and how this process differs from dense architectures—remains unknown. To address this issue, we introduce Gated-LPI (Log-Probability Increase), a neuron-level attribution metric that decomposes log-probability increase across neurons. We present a time-resolved comparison of knowledge acquisition dynamics in MoE and dense architectures, tracking checkpoints over 1.2M (~ 5.0T tokens) and 600K (~ 2.5T tokens) training steps, respectively. Our experiments uncover three patterns: (1) Low-entropy backbone. The top approximately 1% of MoE neurons capture over 45% of positive updates, forming a high-utility core, which is absent in the dense baseline. (2) Early consolidation. The MoE model locks into a stable importance profile within 50% for the dense model, showing that sparsity fosters distributed—rather than brittle—knowledge storage. These patterns collectively demonstrate that sparsity fosters an intrinsically stable and distributed computational backbone from early in training, helping bridge the gap between sparse architectures and training-time interpretability.
AAAI Conference 2026 Conference Paper
Visual Place Recognition (VPR) aims to determine the geographic location of a query image by retrieving its most visually similar counterpart from a geo-tagged reference database. Recently, the emergence of the powerful visual foundation model, DINOv2, trained in a self-supervised manner on massive datasets, has significantly improved VPR performance. This improvement stems from DINOv2’s exceptional feature generalization capabilities but is often accompanied by increased model complexity and computational overhead that impede deployment on resource-constrained devices. To address this challenge, we propose D2-VPR, a Distillation- and Deformable-based framework that retains the strong feature extraction capabilities of visual foundation models while significantly reducing model parameters and achieving a more favorable performance-efficiency trade-off. Specifically, first, we employ a two-stage training strategy that integrates knowledge distillation and fine-tuning. Additionally, we introduce a Distillation Recovery Module (DRM) to better align the feature spaces between the teacher and student models, thereby minimizing knowledge transfer losses to the greatest extent possible. Second, we design a Top-Down-attention-based Deformable Aggregator (TDDA) that leverages global semantic features to dynamically and adaptively adjust the Regions of Interest (ROI) used for aggregation, thereby improving adaptability to irregular structures. Extensive experiments demonstrate that our method achieves competitive performance compared to state-of-the-art approaches. Meanwhile, it reduces the parameter count by approximately 64.2% (compared to CricaVPR).
AAAI Conference 2026 Conference Paper
Federated learning synchronizes models through gradient transmission and aggregation. However, these gradients pose significant privacy risks, as sensitive training data is embedded within them. Existing gradient inversion attacks suffer from significantly degraded reconstruction performance when gradients are perturbed by noise-a common defense mechanism. In this paper, we introduce gradient-guided conditional diffusion models for reconstructing private images from leaked gradients, without prior knowledge of the target data distribution. Our approach leverages the inherent denoising capability of diffusion models to circumvent the partial protection offered by noise perturbation, thereby improving attack performance under such defenses. We further provide a theoretical analysis of the reconstruction error bounds and the convergence properties of the attack loss, characterizing the impact of key factors—such as noise magnitude and attacked model architecture—on reconstruction quality. Extensive experiments demonstrate our attack's superior reconstruction performance with Gaussian noise-perturbed gradients, and confirm our theoretical findings.
AAAI Conference 2026 Conference Paper
Partial linear models (PLM) have attracted much attention for regression estimation and variable selection due to their feasibility on utilizing linear and nonlinear approximations jointly. However, theoretical understanding of how they control the false discovery rate (FDR) during variable selection remains limited. To address this issue, we formulate a new integral-based knockoffs (IKO) inference scheme for controlled variable selection in PLM, where integral-based knockoff statistics are used to measure the variable importance and B-splines (or random Fourier features) are employed for approximating nonlinear components. In theory, FDR control is guaranteed for both linear and nonlinear parts, and the statistical analysis for its power is established. Empirical evaluations validate the effectiveness of our proposed approach.
ICLR Conference 2025 Conference Paper
Detecting training data for large language models (LLMs) is receiving growing attention, especially in applications requiring high reliability. While numerous efforts have been made to address this issue, they typically focus on accuracy without ensuring controllable results. To fill this gap, we propose **K**nockoff Inference-based **T**raining data **D**etector (KTD), a novel method that achieves rigorous false discovery rate (FDR) control in training data detection. Specifically, KTD generates synthetic knockoff samples that seamlessly replace original data points without compromising contextual integrity. A novel knockoff statistic, which incorporates multiple knockoff draws, is then calculated to ensure FDR control while maintaining high power. Our theoretical analysis demonstrates KTD's asymptotic optimality in terms of FDR control and power. Empirical experiments on real-world datasets such as WikiMIA, XSum and Real Time BBC News further validate KTD's superior performance compared to existing methods.
ICML Conference 2025 Conference Paper
While Graph Neural Networks (GNNs) have shown outstanding performance in node classification tasks, they are vulnerable to adversarial attacks, which are imperceptible changes to input samples. Adversarial training, as a widely used tool to enhance the adversarial robustness of GNNs, has presented remarkable effectiveness in node classification tasks. However, the generalization properties for explaining their behaviors remain not well understood from the theoretical viewpoint. To fill this gap, we develop a high probability generalization bound of general GNNs in adversarial learning through covering number analysis. We estimate the covering number of the GNN model class based on the entire perturbed feature matrix by constructing a cover for the perturbation set. Our results are generally applicable to a series of GNNs. We demonstrate their applicability by investigating the generalization performance of several popular GNN models under adversarial attacks, which reveal the architecture-related factors influencing the generalization gap. Our experimental results on benchmark datasets provide evidence that supports the established theoretical findings.
IJCAI Conference 2025 Conference Paper
Recently, numerous methods have been proposed to enhance the robustness of the Graph Convolutional Networks (GCNs) for their vulnerability against adversarial attacks. Despite their empirical success, a significant gap remains in understanding GCNs' adversarial robustness from the theoretical perspective. This paper addresses this gap by analyzing generalization against both node and structure attacks for multi-layer GCNs through the framework of uniform stability. Under the smoothness assumption of the loss function, we establish the first adversarial generalization bound of GCNs in expectation. Our theoretical analysis contributes to a deeper understanding of how adversarial perturbations and graph architectures influence generalization performance, which provides meaningful insights for designing robust models. Experimental results on benchmark datasets confirm the validity of our theoretical findings, highlighting their practical significance.
AAAI Conference 2025 Conference Paper
Cross-domain recommendation (CDR) mitigates data sparsity and cold-start issues in recommendation systems. While recent CDR approaches using graph neural networks (GNNs) capture complex user-item interactions, they rely on manually designed architectures that are often suboptimal and labor-intensive. Additionally, extracting valuable behavioral information from source domains to improve target domain recommendations remains challenging. To address these challenges, we propose Behavior importance-aware Graph Neural Architecture Search (BiGNAS), a framework that jointly optimizes GNN architecture and data importance for CDR. BiGNAS introduces two key components: a Cross-Domain Customized Supernetwork and a Graph-Based Behavior Importance Perceptron. The supernetwork, as a one-shot, retrain-free module, automatically searches the optimal GNN architecture for each domain without the need for retraining. The perceptron uses auxiliary learning to dynamically assess the importance of source domain behaviors, thereby improving target domain recommendations. Extensive experiments on benchmark CDR datasets and a large-scale industry advertising dataset demonstrate that BiGNAS consistently outperforms state-of-the-art baselines. To the best of our knowledge, this is the first work to jointly optimize GNN architecture and behavior data importance for cross-domain recommendation.
ICRA Conference 2025 Conference Paper
Vehicle-to-everything technologies (V2X) have become an ideal paradigm to extend the perception range and see through the occlusion. Exiting efforts focus on single-frame cooperative perception, however, how to capture the temporal cue between frames with V2X to facilitate the prediction task even the planning task is still underexplored. In this paper, we introduce the Co-MTP, a general cooperative trajectory prediction framework with multi-temporal fusion for autonomous driving, which leverages the V2X system to fully capture the interaction among agents in both history and future domains to benefit the planning. In the history domain, V2X can complement the incomplete history trajectory in single-vehicle perception, and we design a heterogeneous graph transformer to learn the fusion of the history feature from multiple agents and capture the history interaction. Moreover, the goal of prediction is to support future planning. Thus, in the future domain, V2X can provide the prediction results of surrounding objects, and we further extend the graph transformer to capture the future interaction among the ego planning and the other vehicles' intentions and obtain the final future scenario state under a certain planning action. We evaluate the Co-MTP framework on the real-world dataset V2X-Seq, and the results show that Co-MTP achieves state-of-the-art performance and that both history and future fusion can greatly benefit prediction. Our code is available on our project website: https://xiaomiaozhang.github.io/Co-MTP/
AAAI Conference 2025 Conference Paper
In recent years, there have been a growing number of works studying the generalization properties of stochastic gradient descent (SGD) from the perspective of algorithmic stability. However, few of them devote to simultaneously studying the generalization and optimization for the non-convex setting, especially pairwise SGD with heavy-tailed gradient noise. This paper considers the impact of the heavy-tailed gradient noise obeying sub-Weibull distribution on the stability-based learning guarantees for non-convex pairwise SGD by investigating its generalization and optimization jointly. Specifically, based on two novel pairwise uniform model stability tools, we firstly bound the generalization error of pairwise SGD in the general non-convex setting after bridging the quantitative relationships between stability and generalization error. Then, we further consider the practical heavy-tailed sub-Weibull gradient noise condition to establish a refined generalization bound without the bounded gradient condition. Finally, sharper error bounds for generalization and optimization are built by introducing the gradient dominance condition. Comparing these results reveals that sub-Weibull gradient noise brings some positive dependencies on the heavy-tailed strength for generalization and optimization. Furthermore, we extend our analysis to the corresponding pairwise minibatch SGD and derive the first stability-based near-optimal generalization and optimization bounds which are consistent with many empirical observations.
ICML Conference 2025 Conference Paper
In recent years, contrastive learning has achieved state-of-the-art performance in the territory of self-supervised representation learning. Many previous works have attempted to provide the theoretical understanding underlying the success of contrastive learning. Almost all of them rely on a default assumption, i. e. , the label consistency assumption, which may not hold in practice (the probability of failure is called labeling error) due to the strength and randomness of common augmentation strategies, such as random resized crop (RRC). This paper investigates the theoretical impact of labeling error on the downstream classification performance of contrastive learning. We first reveal several significant negative impacts of labeling error on downstream classification risk. To mitigate these impacts, data dimensionality reduction method (e. g. , singular value decomposition, SVD) is applied on original data to reduce false positive samples, and establish both theoretical and empirical evaluations. Moreover, it is also found that SVD acts as a double-edged sword, which may lead to the deterioration of downstream classification accuracy due to the reduced connectivity of the augmentation graph. Based on the above observations, we give the augmentation suggestion that we should use some moderate embedding dimension (such as $512, 1024$ in our experiments), data inflation, weak augmentation, and SVD to ensure large graph connectivity and small labeling error to improve model performance.
AAAI Conference 2025 Conference Paper
Video corpus grounding (VCG), which aims to retrieve relevant video moments from a video corpus, has attracted significant attention in the multimedia research community. However, the existing VCG setting primarily focuses on matching textual descriptions with videos and ignores the distinct visual identities in the videos, thus resulting in inaccurate understanding of video content and deteriorated retrieval performances. To address this limitation, we introduce a novel task, Identity-Text Video Corpus Grounding (ITVCG), which simultaneously utilize textual descriptions and visual identities as queries. As such, ITVCG benefits in enabling more accurate video corpus grounding with visual identities, as well as providing users with more flexible options to locate relevant frames based on either textual descriptions or textual descriptions and visual identities. To conduct evaluations regarding the novel ITVCG task, we propose the TVR-IT dataset, comprising 463 identity images from 6 TV shows, with 68,840 out of 72,840 queries containing at least one identity image. Furthermore, we propose Video-Locator, the first model designed for the ITVCG task. Our proposed Video-Locator integrates video-identity-text alignment and multi-modal fine-grained fusion components, facilitating a video large language model (Video LLM) to jointly understand textual descriptions, visual identities, as well as videos. Experimental results demonstrate the effectiveness of the proposed Video-Locator model and highlight the importance of identity-generalization capability for ITVCG.
AAAI Conference 2025 Conference Paper
Partially linear models (PLM) have attracted much attention in the field of statistical machine learning. Specially, the ability of variable selection of PLM has been studied extensively due to the high requirement of model interpretability. However, few of the existing works concerns the false discovery rate (FDR) controllability of variable selection associated with PLM. To address this issue, we formulate a new Knockoffs Inference scheme for Linear And Nonlinear Discoverer (called KI-LAND), where FDR is controlled with respect to both linear and nonlinear variables for automatic structure discovery. For the proposed KI-LAND, theoretical guarantees are established for both FDR controllability and power, and experimental evaluations are provided to validate its effectiveness.
AAAI Conference 2025 Conference Paper
Text-to-Video generation, which utilizes the provided text prompt to generate high-quality videos, has drawn increasing attention and achieved great success due to the development of diffusion models recently. Existing methods mainly rely on a pre-trained text encoder to capture the semantic information and perform cross attention with the encoded text prompt to guide the generation of video. However, when it comes to complex prompts that contain dynamic scenes and multiple camera-view transformations, these methods can not decompose the overall information into separate scenes, as well as fail to smoothly change scenes based on the corresponding camera-views. To solve these problems, we propose a novel method, i.e., Modular-Cam. Specifically, to better understand a given complex prompt, we utilize a large language model to analyze user instructions and decouple them into multiple scenes together with transition actions. To generate a video containing dynamic scenes that match the given camera-views, we incorporate the widely-used temporal transformer into the diffusion model to ensure continuity within a single scene and propose CamOperator, a modular network based module that well controls the camera movements. Moreover, we propose AdaControlNet, which utilizes ControlNet to ensure consistency across scenes and adaptively adjusts the color tone of the generated video. Extensive qualitative and quantitative experiments prove our proposed Modular-Cam's strong capability of generating multi-scene videos together with its ability to achieve fine-grained control of camera movements. Generated results are available at https://modular-cam.github.io.
AAAI Conference 2025 Conference Paper
Clustering traditionally aims to reveal a natural grouping structure within unlabeled data. However, this structure may not always align with users' preferences. In this paper, we propose a personalized clustering method that explicitly performs targeted representation learning by interacting with users via modicum task information (e.g., must-link or cannot-link pairs) to guide the clustering direction. We query users with the most informative pairs, i.e., those pairs most hard to cluster and those most easy to miscluster, to facilitate the representation learning in terms of the clustering preference. Moreover, by exploiting attention mechanism, the targeted representation is learned and augmented. By leveraging the targeted representation and constrained contrastive loss as well, personalized clustering is obtained. Theoretically, we verify that the risk of personalized clustering is tightly bounded, guaranteeing that active queries to users do mitigate the clustering risk. Experimentally, extensive results show that our method performs well across different clustering tasks and datasets, even when only a limited number of queries are available.
AAAI Conference 2025 Conference Paper
Catastrophic forgetting is a key challenge in incremental named entity recognition (INER). Existing methods often address this issue through distillation-based approaches, which involve transferring previously learned knowledge from the old model to the new one. However, these methods may not fully equip the new model with an adequate understanding of the characteristics about old entity types, leading to confusion when classifying tokens associated with these entity types. To address this challenge, we propose a novel method called Prototypical Replay with Old-class Focusing Knowledge Distillation (POF) for INER. Our approach focuses on preserving the main characteristics of each previous entity type by storing compact prototypes and replaying them with appropriate frequency. This replay strategy makes the new model review the knowledge of old entity types while minimizing storage needs. Additionally, we introduce an old-class focusing knowledge distillation (OFKD) loss, which distills features only in old-class regions to maintain the quality of old-class prototypes and prevent ineffective prototypical replay while preserving sufficient plasticity for learning new entity types. We conducted experiments on three benchmark datasets (i.e., Few-NERD, I2B2 and OntoNotes5), and the results demonstrate that our method outperforms all previous state-of-the-art methods.
EAAI Journal 2025 Journal Article
Deep learning-based computer vision models are increasingly being used in safety-critical domains, such as autonomous driving, which has led to concerns about the trustworthiness and explainability of these models. Recently, synthetic visual counterfactual explanations have been proposed to uncover the decision-making processes of these models. Building upon this foundation, This study introduces a novel two-stage semantic Shapley-based counterfactual explanation (SSCE) scheme to generate explanations for significant semantics in complex scenarios. In the first stage, the semantic Shapley of the input image is generated to identify the most critical semantic regions. In the second stage, a counterfactual explanation of critical semantics is produced using current synthetic counterfactual explanation methods. Extensive experiments on an end-to-end autonomous driving decision model validate the ability of SSCE to provide realistic, sparse, and proximate counterfactual explanations in complex scenarios.
ICML Conference 2025 Conference Paper
Spiking Neural Networks (SNNs) have demonstrated remarkable potential across many domains, including computer vision and natural language processing, owing to their energy efficiency and biological plausibility. However, their application in long-term prediction tasks remains underexplored, which is primarily due to two critical challenges: (1) current SNN encoding methods are unable to effectively encode long temporal information, leading to increased computational complexity and energy consumption; (2) though Transformer-based models have achieved state-of-the-art accuracy in temporal prediction tasks, the absence of proper positional encoding for spiking self-attention restricts Spiking Transformer from effectively utilizing positional information, resulting in performance degradation. To address these challenges, we introduce an attention-free framework, Spik ing F ourier Network ( SpikF ), that encodes input sequences in patches and employs an innovative frequency domain selection mechanism to effectively utilize the sequential properties of time-series data. Extensive evaluations on eight well-established long-term prediction datasets demonstrate that SpikF achieves an averaged $1. 9\%$ reduction in Mean Absolute Error (MAE) compared to state-of-the-art models, while lowering total energy consumption by $3. 16\times$. Our code is available at https: //github. com/WWJ-creator/SpikF.
YNIMG Journal 2025 Journal Article
This study investigates the differences in effective neural connections during food inhibitory control between individuals with overweight/obesity (OW/OB) and those with normal weight (NW), and examines how these neural differences relate to daily eating behaviors. Fifty-one female participants were classified into OW/OB (BMI ≥ 25 kg/m²) or NW (BMI 18-22 kg/m²) groups. Participants completed a modified food-specific go/no-go task with working memory load during fMRI scanning. Neural connectivity was analyzed using dynamic causal modelling (DCM). Ecological momentary assessment (EMA) was used to collect real-time data on eating behaviors over one week. The OW/OB group showed lower accuracy in responding to low-calorie food cues and greater activation in the left hippocampus during no-go trials with high-calorie foods. DCM revealed stronger excitatory connectivity from the right inferior frontal gyrus (IFG) to the medial prefrontal cortex (mPFC), and stronger inhibitory connectivity from the mPFC to the dorsal caudate, as well as from the dorsal caudate to the left hippocampus in the OW/OB group. EMA results indicated that the OW/OB group was more likely to succumb to food desires between 13:00 and 17:00. Mediation analysis confirmed that effective connectivity mediated the relationship between task performance and daily eating behaviors. These findings elucidate the neural mechanisms underlying food inhibitory control in OW/OB individuals, highlighting the role of the hippocampus and the IFG-mPFC circuit. The study provides theoretical advances within the dual-system framework and suggests that targeting these neural pathways may improve dietary control in obesity.
IJCAI Conference 2025 Conference Paper
Recently, the mathematical tool from fractal geometry (i. e. , fractal dimension) has been employed to investigate optimization trajectory-dependent generalization ability for some pointwise learning models with independent and identically distributed (i. i. d. ) observations. This paper goes beyond the limitations of pointwise learning and i. i. d. samples, and establishes generalization bounds for pairwise learning with uniformly strong mixing samples. The derived theoretical results fill the gap of trajectory-dependent generalization analysis for pairwise learning, and can be applied to wide learning paradigms, e. g. , metric learning, ranking and gradient learning. Technically, our framework brings concentration estimation with Rademacher complexity and trajectory-dependent fractal dimension together in a coherent way for felicitous learning theory analysis. In addition, the efficient computation of fractal dimension can be guaranteed for random algorithms (e. g. , stochastic gradient descent algorithm for deep neural networks) by bridging topological data analysis tools and the trajectory-dependent fractal dimension.
IJCAI Conference 2024 Conference Paper
Stochastic bilevel optimization (SBO) has been integrated into many machine learning paradigms recently including hyperparameter optimization, meta learning, reinforcement learning, etc. Along with the wide range of applications, there have been abundant studies on concerning the computing behaviors of SBO. However, the generalization guarantees of SBO methods are far less understood from the lens of statistical learning theory. In this paper, we provide a systematical generalization analysis of the first-order gradient-based bilevel optimization methods. Firstly, we establish the quantitative connections between the on-average argument stability and the generalization gap of SBO methods. Then, we derive the upper bounds of on-average argument stability for single timescale stochastic gradient descent (SGD) and two timescale SGD, where three settings (nonconvex-nonconvex (NC-NC), convex-convex (C-C) and strongly-convex-strongly-convex (SC-SC)) are considered respectively. Experimental analysis validates our theoretical findings. Compared with the previous algorithmic stability analysis, our results do not require the re-initialization of the inner-level parameters before each iteration and are suit for more general objective functions.
NeurIPS Conference 2024 Conference Paper
Stochastic compositional optimization (SCO) problem constitutes a class of optimization problems characterized by the objective function with a compositional form, including the tasks with known derivatives, such as AUC maximization, and the derivative-free tasks exemplified by black-box vertical federated learning (VFL). From the learning theory perspective, the learning guarantees of SCO algorithms with known derivatives have been studied in the literature. However, the potential impacts of the derivative-free setting on the learning guarantees of SCO remains unclear and merits further investigation. This paper aims to reveal the impacts by developing a theoretical analysis for two derivative-free algorithms, black-box SCGD and SCSC. Specifically, we first provide the sharper generalization upper bounds of convex SCGD and SCSC based on a new stability analysis framework more effective than prior work under some milder conditions, which is further developed to the non-convex case using the almost co-coercivity property of smooth function. Then, we derive the learning guarantees of three black-box variants of non-convex SCGD and SCSC with additional optimization analysis. Comparing these results, we theoretically uncover the impacts that a better gradient estimation brings a tighter learning guarantee and a larger proportion of unknown gradients may lead to a stronger dependence on the gradient estimation quality. Finally, our analysis is applied to two SCO algorithms, FOO-based vertical VFL and VFL-CZOFO, to build the first learning guarantees for VFL that align with the findings of SCGD and SCSC.
YNIMG Journal 2024 Journal Article
Obesity has a profound impact on metabolic health thereby adversely affecting brain structure and function. However, the majority of previous studies used a single structural index to investigate the link between brain structure and body mass index (BMI), which hinders our understanding of structural covariance between regions in obesity. This study aimed to examine the relationship between macroscale cortical organization and BMI using novel morphometric similarity networks (MSNs). The individual MSNs were first constructed from individual eight multimodal cortical morphometric features between brain regions. Then the relationship between BMI and MSNs within the discovery sample of 434 participants was assessed. The key findings were further validated in an independent sample of 192 participants. We observed that the lateral non-reward orbitofrontal cortex (lOFC) exhibited decoupling (i.e., reduction in integration) in obesity, which was mainly manifested by its decoupling with the cognitive systems (i.e., DMN and FPN) while the medial reward orbitofrontal cortex (mOFC) showed de-differentiation (i.e., decrease in distinctiveness) in obesity, which was mainly represented by its de-differentiation with the cognitive and attention systems (i.e., DMN and VAN). Additionally, the lOFC showed de-differentiation with the visual system in obesity, while the mOFC showed decoupling with the visual system and hyper-coupling with the sensory-motor system in obesity. As an important first step in revealing the role of underlying structural covariance in body mass variability, the present study presents a novel mechanism that underlies the reward-control interaction imbalance in obesity, thus can inform future weight-management approaches.
IJCAI Conference 2024 Conference Paper
Recently, the enhancement on the adversarial robustness of machine learning algorithms has gained significant attention across various application domains. Given the widespread label scarcity issue in real-world data, adversarial contrastive learning (ACL) has been proposed to adversarially train robust models using unlabeled data. Despite the empirical success, its generalization behavior remains poorly understood and far from being well-characterized. This paper aims to address this issue from a learning theory perspective. We establish novel high-probability generalization bounds for the general Lipschitz loss functions. The derived bounds scale O(log(k)) with respect to the number of negative samples k, which improves the existing linear dependency bounds. Our results are generally applicable to many prediction models, including linear models and deep neural networks. In particular, we obtain an optimistic generalization bound O(1/n) under the smoothness assumption of the loss function on the sample size n. To the best of our knowledge, this is the first fast-rate bound valid for ACL. Empirical evaluations on real-world datasets verify our theoretical findings.
AAAI Conference 2024 Conference Paper
Decentralized Stochastic Gradient Descent (D-SGD) represents an efficient communication approach tailored for mastering insights from vast, distributed datasets. Inspired by parallel optimization paradigms, the incorporation of minibatch serves to diminish variance, consequently expediting the optimization process. Nevertheless, as per our current understanding, the existing literature has not thoroughly explored the learning theory foundation of Decentralized Minibatch Stochastic Gradient Descent (DM-SGD). In this paper, we try to address this theoretical gap by investigating the generalization properties of DM-SGD. We establish the sharper generalization bounds for the DM-SGD algorithm with replacement (without replacement) on (non)convex and (non)smooth cases. Moreover, our results consistently recover to the results of Centralized Stochastic Gradient Descent (C-SGD). In addition, we derive generalization analysis for Zero-Order (ZO) version of DM-SGD.
NeurIPS Conference 2024 Conference Paper
Existing Video Corpus Moment Retrieval (VCMR) is limited to coarse-grained understanding that hinders precise video moment localization when given fine-grained queries. In this paper, we propose a more challenging fine-grained VCMR benchmark requiring methods to localize the best-matched moment from the corpus with other partially matched candidates. To improve the dataset construction efficiency and guarantee high-quality data annotations, we propose VERIFIED, an automatic \underline{V}id\underline{E}o-text annotation pipeline to generate captions with \underline{R}el\underline{I}able \underline{FI}n\underline{E}-grained statics and \underline{D}ynamics. Specifically, we resort to large language models (LLM) and large multimodal models (LMM) with our proposed Statics and Dynamics Enhanced Captioning modules to generate diverse fine-grained captions for each video. To filter out the inaccurate annotations caused by the LLM hallucination, we propose a Fine-Granularity Aware Noise Evaluator where we fine-tune a video foundation model with disturbed hard-negatives augmented contrastive and matching losses. With VERIFIED, we construct a more challenging fine-grained VCMR benchmark containing Charades-FIG, DiDeMo-FIG, and ActivityNet-FIG which demonstrate a high level of annotation quality. We evaluate several state-of-the-art VCMR models on the proposed dataset, revealing that there is still significant scope for fine-grained video understanding in VCMR.
JBHI Journal 2023 Journal Article
Research on orthodontic treatment monitoring from oralscan video is a new direction in dental digitalization. We designed an approach to reconstruct, segment, and estimate the pose of individual teeth to measure orthodontic treatment. To handle the semantic gap in heterogeneous data on the condition that they are combined linearly, we present a multimedia interaction network (MIN) to combine heterogeneous information in point cloud segmentation by extending the graph attention mechanism. Moreover, a structure-aware quadruple loss is designed to explore the relation between multiple and diverse unmatched points in point cloud registration. The performance of our approach is evaluated on multiple tooth registration datasets, and extensive experiments show that our approach improves the accuracy by a margin of 1. 4% in the inlier ratio on the Aoralscan3 dataset when it is compared with prevailing approaches.
AAAI Conference 2023 Conference Paper
Video Grounding (VG) aims to locate the desired segment from a video given a sentence query. Recent studies have found that current VG models are prone to over-rely the groundtruth moment annotation distribution biases in the training set. To discourage the standard VG model's behavior of exploiting such temporal annotation biases and improve the model generalization ability, we propose multiple negative augmentations in a hierarchical way, including cross-video augmentations from clip-/video-level, and self-shuffled augmentations with masks. These augmentations can effectively diversify the data distribution so that the model can make more reasonable predictions instead of merely fitting the temporal biases. However, directly adopting such data augmentation strategy may inevitably carry some noise shown in our cases, since not all of the handcrafted augmentations are semantically irrelevant to the groundtruth video. To further denoise and improve the grounding accuracy, we design a multi-stage curriculum strategy to adaptively train the standard VG model from easy to hard negative augmentations. Experiments on newly collected Charades-CD and ActivityNet-CD datasets demonstrate our proposed strategy can improve the performance of the base model on both i.i.d and o.o.d scenarios.
AAAI Conference 2023 Conference Paper
Federated Learning, as a popular paradigm for collaborative training, is vulnerable against privacy attacks. Different privacy levels regarding users' attitudes need to be satisfied locally, while a strict privacy guarantee for the global model is also required centrally. Personalized Local Differential Privacy (PLDP) is suitable for preserving users' varying local privacy, yet only provides a central privacy guarantee equivalent to the worst-case local privacy level. Thus, achieving strong central privacy as well as personalized local privacy with a utility-promising model is a challenging problem. In this work, a general framework (APES) is built up to strengthen model privacy under personalized local privacy by leveraging the privacy amplification effect of the shuffle model. To tighten the privacy bound, we quantify the heterogeneous contributions to the central privacy user by user. The contributions are characterized by the ability of generating “echos” from the perturbation of each user, which is carefully measured by proposed methods Neighbor Divergence and Clip-Laplace Mechanism. Furthermore, we propose a refined framework (S-APES) with the post-sparsification technique to reduce privacy loss in high-dimension scenarios. To the best of our knowledge, the impact of shuffling on personalized local privacy is considered for the first time. We provide a strong privacy amplification effect, and the bound is tighter than the baseline result based on existing methods for uniform local privacy. Experiments demonstrate that our frameworks ensure comparable or higher accuracy for the global model.
NeurIPS Conference 2023 Conference Paper
Federated zeroth-order optimization (FedZO) algorithm enjoys the advantages of both zeroth-order optimization and federated learning, and has shown exceptional performance on black-box attack and softmax regression tasks. However, there is no generalization analysis for FedZO, and its analysis on computing convergence rate is slower than the corresponding first-order optimization setting. This paper aims to establish systematic theoretical assessments of FedZO by developing the analysis technique of on-average model stability. We establish the first generalization error bound of FedZO under the Lipschitz continuity and smoothness conditions. Then, refined generalization and optimization bounds are provided by replacing bounded gradient with heavy-tailed gradient noise and utilizing the second-order Taylor expansion for gradient approximation. With the help of a new error decomposition strategy, our theoretical analysis is also extended to the asynchronous case. For FedZO, our fine-grained analysis fills the theoretical gap on the generalization guarantees and polishes the convergence characterization of the computing algorithm.
IJCAI Conference 2023 Conference Paper
Recently, adversarial metric learning has been proposed to enhance the robustness of the learned distance metric against adversarial perturbations. Despite rapid progress in validating its effectiveness empirically, theoretical guarantees on adversarial robustness and generalization are far less understood. To fill this gap, this paper focuses on unveiling the generalization properties of adversarial metric learning by developing the uniform convergence analysis techniques. Based on the capacity estimation of covering numbers, we establish the first high-probability generalization bounds with order O(n^{-1/2}) for adversarial metric learning with pairwise perturbations and general losses, where n is the number of training samples. Moreover, we obtain the refined generalization bounds with order O(n^{-1}) for the smooth loss by using local Rademacher complexity, which is faster than the previous result of adversarial pairwise learning, e. g. , adversarial bipartite ranking. Experimental evaluation on real-world datasets validates our theoretical findings.
NeurIPS Conference 2023 Conference Paper
Current auxiliary learning methods mainly adopt the methodology of reweighing losses for the manually collected auxiliary data and tasks. However, these methods heavily rely on domain knowledge during data collection, which may be hardly available in reality. Therefore, current methods will become less effective and even do harm to the primary task when unhelpful auxiliary data and tasks are employed. To tackle the problem, we propose a joint data-task generation framework for auxiliary learning (DTG-AuxL), which can bring benefits to the primary task by generating the new auxiliary data and task in a joint manner. The proposed DTG-AuxL framework contains a joint generator and a bi-level optimization strategy. Specifically, the joint generator contains a feature generator and a label generator, which are designed to be applicable and expressive for various auxiliary learning scenarios. The bi-level optimization strategy optimizes the joint generator and the task learning model, where the joint generator is effectively optimized in the upper level via the implicit gradient from the primary loss and the explicit gradient of our proposed instance regularization, while the task learning model is optimized in the lower level by the generated data and task. Extensive experiments show that our proposed DTG-AuxL framework consistently outperforms existing methods in various auxiliary learning scenarios, particularly when the manually collected auxiliary data and tasks are unhelpful.
NeurIPS Conference 2023 Conference Paper
Graph neural architecture search (GraphNAS) has shown great potential for automatically designing graph neural architectures for graph related tasks. However, multi-task GraphNAS capable of handling multiple tasks simultaneously has been largely unexplored in literature, posing great challenges to capture the complex relations and influences among different tasks. To tackle this problem, we propose a novel multi-task graph neural architecture search with task-aware collaboration and curriculum (MTGC3), which is able to simultaneously discover optimal architectures for different tasks and learn the collaborative relationships among different tasks in a joint manner. Specifically, we design the layer-wise disentangled supernet capable of managing multiple architectures in a unified framework, which combines with our proposed soft task-collaborative module to learn the transferability relationships between tasks. We further develop the task-wise curriculum training strategy to improve the architecture search procedure via reweighing the influence of different tasks based on task difficulties. Extensive experiments show that our proposed MTGC3 model achieves state-of-the-art performance against several baselines in multi-task scenarios, demonstrating its ability to discover effective architectures and capture the collaborative relationships for multiple tasks.
AAAI Conference 2023 Conference Paper
Triplet learning, i.e. learning from triplet data, has attracted much attention in computer vision tasks with an extremely large number of categories, e.g., face recognition and person re-identification. Albeit with rapid progress in designing and applying triplet learning algorithms, there is a lacking study on the theoretical understanding of their generalization performance. To fill this gap, this paper investigates the generalization guarantees of triplet learning by leveraging the stability analysis. Specifically, we establish the first general high-probability generalization bound for the triplet learning algorithm satisfying the uniform stability, and then obtain the excess risk bounds of the order O(log(n)/(√n) ) for both stochastic gradient descent (SGD) and regularized risk minimization (RRM), where 2n is approximately equal to the number of training samples. Moreover, an optimistic generalization bound in expectation as fast as O(1/n) is derived for RRM in a low noise case via the on-average stability analysis. Finally, our results are applied to triplet metric learning to characterize its theoretical underpinning.
AAAI Conference 2023 Conference Paper
One of the recent best attempts at Text-to-SQL is the pre-trained language model. Due to the structural property of the SQL queries, the seq2seq model takes the responsibility of parsing both the schema items (i.e., tables and columns) and the skeleton (i.e., SQL keywords). Such coupled targets increase the difficulty of parsing the correct SQL queries especially when they involve many schema items and logic operators. This paper proposes a ranking-enhanced encoding and skeleton-aware decoding framework to decouple the schema linking and the skeleton parsing. Specifically, for a seq2seq encoder-decode model, its encoder is injected by the most relevant schema items instead of the whole unordered ones, which could alleviate the schema linking effort during SQL parsing, and its decoder first generates the skeleton and then the actual SQL query, which could implicitly constrain the SQL parsing. We evaluate our proposed framework on Spider and its three robustness variants: Spider-DK, Spider-Syn, and Spider-Realistic. The experimental results show that our framework delivers promising performance and robustness. Our code is available at https://github.com/RUCKBReasoning/RESDSQL.
AAAI Conference 2023 Conference Paper
The matrix-based Rényi's entropy allows us to directly quantify information measures from given data, without explicit estimation of the underlying probability distribution. This intriguing property makes it widely applied in statistical inference and machine learning tasks. However, this information theoretical quantity is not robust against noise in the data, and is computationally prohibitive in large-scale applications. To address these issues, we propose a novel measure of information, termed low-rank matrix-based Rényi's entropy, based on low-rank representations of infinitely divisible kernel matrices. The proposed entropy functional inherits the specialty of of the original definition to directly quantify information from data, but enjoys additional advantages including robustness and effective calculation. Specifically, our low-rank variant is more sensitive to informative perturbations induced by changes in underlying distributions, while being insensitive to uninformative ones caused by noises. Moreover, low-rank Rényi's entropy can be efficiently approximated by random projection and Lanczos iteration techniques, reducing the overall complexity from O(n³) to O(n²s) or even O(ns²), where n is the number of data samples and s ≪ n. We conduct large-scale experiments to evaluate the effectiveness of this new information measure, demonstrating superior results compared to matrix-based Rényi's entropy in terms of both performance and computational efficiency.
AAAI Conference 2023 Conference Paper
Recently, some mixture algorithms of pointwise and pairwise learning (PPL) have been formulated by employing the hybrid error metric of “pointwise loss + pairwise loss” and have shown empirical effectiveness on feature selection, ranking and recommendation tasks. However, to the best of our knowledge, the learning theory foundation of PPL has not been touched in the existing works. In this paper, we try to fill this theoretical gap by investigating the generalization properties of PPL. After extending the definitions of algorithmic stability to the PPL setting, we establish the high-probability generalization bounds for uniformly stable PPL algorithms. Moreover, explicit convergence rates of stochastic gradient descent (SGD) and regularized risk minimization (RRM) for PPL are stated by developing the stability analysis technique of pairwise learning. In addition, the refined generalization bounds of PPL are obtained by replacing uniform stability with on-average stability.
AAAI Conference 2023 Conference Paper
Sorted L-One Penalized Estimation (SLOPE) has shown the nice theoretical property as well as empirical behavior recently on the false discovery rate (FDR) control of high-dimensional feature selection by adaptively imposing the non-increasing sequence of tuning parameters on the sorted L1 penalties. This paper goes beyond the previous concern limited to the FDR control by considering the stepdown-based SLOPE in order to control the probability of k or more false rejections (k-FWER) and the false discovery proportion (FDP). Two new SLOPEs, called k-SLOPE and F-SLOPE, are proposed to realize k-FWER and FDP control respectively, where the stepdown procedure is injected into the SLOPE scheme. For the proposed stepdown SLOPEs, we establish their theoretical guarantees on controlling k-FWER and FDP under the orthogonal design setting, and also provide an intuitive guideline for the choice of regularization parameter sequence in much general setting. Empirical evaluations on simulated data validate the effectiveness of our approaches on controlled feature selection and support our theoretical findings.
IJCAI Conference 2023 Conference Paper
Recently, information-theoretic analysis has become a popular framework for understanding the generalization behavior of deep neural networks. It allows a direct analysis for stochastic gradient / Langevin descent (SGD/SGLD) learning algorithms without strong assumptions such as Lipschitz or convexity conditions. However, the current generalization error bounds within this framework are still far from optimal, while substantial improvements on these bounds are quite challenging due to the intractability of high-dimensional information quantities. To address this issue, we first propose a novel information theoretical measure: kernelized Rényi's entropy, by utilizing operator representation in Hilbert space. It inherits the properties of Shannon's entropy and can be effectively calculated via simple random sampling, while remaining independent of the input dimension. We then establish the generalization error bounds for SGD/SGLD under kernelized Rényi's entropy, where the mutual information quantities can be directly calculated, enabling evaluation of the tightness of each intermediate step. We show that our information-theoretical bounds depend on the statistics of the stochastic gradients evaluated along with the iterates, and are rigorously tighter than the current state-of-the-art (SOTA) results. The theoretical findings are also supported by large-scale empirical studies.
AAAI Conference 2022 Conference Paper
Expert finding, a popular service provided by many online websites such as Expertise Finder, LinkedIn, and AMiner, is beneficial to seeking candidate qualifications, consultants, and collaborators. However, its quality is suffered from lack of ample sources of expert information. This paper employs AMiner as the basis with an aim at linking any external experts to the counterparts on AMiner. As it is infeasible to acquire sufficient linkages from arbitrary external sources, we explore the problem of zero-shot expert linking. In this paper, we propose CODE, which first pre-trains an expert linking model by contrastive learning on AMiner such that it can capture the representation and matching patterns of experts without supervised signals, then it is fine-tuned between AMiner and external sources to enhance the model’s transferability in an adversarial manner. For evaluation, we first design two intrinsic tasks, author identification and paper clustering, to validate the representation and matching capability endowed by contrastive learning. Then the final external expert linking performance on two genres of external sources also implies the superiority of the adversarial fine-tuning method. Additionally, we show the online deployment of CODE, and continuously improve its online performance via active learning.
TCS Journal 2022 Journal Article
Connectivity of a connected graph G, κ ( G ), is an important index in exploring network topology which is the minimal number of vertices that need to be removed to separate G into disconnected or trivial. Let G 0, G 1, …, G m − 1 be m connected graphs of the same order. A matching composition network G is constructed by adding an arbitrary perfect matching between G 0 and G 1. For m ≥ 3, a cycle composition network H is constructed by adding an arbitrary perfect matching between G i and G i + 1 ( mod m ) for each 0 ≤ i ≤ m − 1. This construction has been so widely used in literature to build networks in which fault diagnosability can be studied, that it is worth to study their connectivity in detail, this is the main purpose of this paper. In this paper, we determine (1) κ ( G ) = δ ( G ) if κ ( G 0 ) + κ ( G 1 ) ≥ δ ( G ); otherwise, κ ( G ) ≥ κ ( G 0 ) + κ ( G 1 ), and (2) κ ( H ) = δ ( H ) if ∑ i = 0 m − 1 κ ( G i ) ≥ δ ( H ); otherwise, κ ( H ) ≥ ∑ i = 0 m − 1 κ ( G i ). Examples show those bounds are tight. We then generalize these examples to a general composition using matchings on which we propose a conjecture on the connectivity and prove it for an important particular case.
AAAI Conference 2022 Conference Paper
Recently, the scheme of model-X knockoffs was proposed as a promising solution to address controlled feature selection under high-dimensional finite-sample settings. However, the procedure of model-X knockoffs depends heavily on the coefficient-based feature importance and only concerns the control of false discovery rate (FDR). To further improve its adaptivity and flexibility, in this paper, we propose an error-based knockoff inference method by integrating the knockoff features, the error-based feature importance statistics, and the stepdown procedure together. The proposed inference procedure does not require specifying a regression model and can handle feature selection with theoretical guarantees on controlling false discovery proportion (FDP), FDR, or k-familywise error rate (k-FWER). Empirical evaluations demonstrate the competitive performance of our approach on both simulated and real data.
IJCAI Conference 2022 Conference Paper
Partial label learning (PLL) is to learn a discriminative model under incomplete supervision, where each instance is annotated with a candidate label set. The basic principle of PLL is that the unknown correct label y of an instance x resides in its candidate label set s, i. e. , P(y ∈ s | x) = 1. On which basis, current researches either directly model P(x | y) under different data generation assumptions or propose various surrogate multiclass losses, which all aim to encourage the model-based Pθ(y ∈ s | x)→1 implicitly. In this work, instead, we explicitly construct a binary classification task toward P(y ∈ s | x) based on the discriminative model, that is to predict whether the model-output label of x is one of its candidate labels. We formulate a novel risk estimator with estimation error bound for the proposed PLL binary classification risk. By applying logit adjustment based on disambiguation strategy, the practical approach directly maximizes Pθ(y ∈ s | x) while implicitly disambiguating the correct one from candidate labels simultaneously. Thorough experiments validate that the proposed approach achieves competitive performance against the state-of-the-art PLL methods.
NeurIPS Conference 2022 Conference Paper
Auxiliary learning is a widely adopted practice in deep learning, which aims to improve the model performance on the primary task by exploiting the beneficial information in the auxiliary loss. Existing auxiliary learning methods only focus on balancing the auxiliary loss and the primary loss, ignoring the module-level auxiliary influence, i. e. , an auxiliary loss will be beneficial for optimizing specific modules within the model but harmful to others, failing to make full use of auxiliary information. To tackle the problem, we propose a Module-Aware Optimization approach for Auxiliary Learning (MAOAL). The proposed approach considers the module-level influence through the learnable module-level auxiliary importance, i. e. , the importance of each auxiliary loss to each module. Specifically, the proposed approach jointly optimizes the module-level auxiliary importance and the model parameters in a bi-level manner. In the lower optimization, the model parameters are optimized with the importance parameterized gradient, while in the upper optimization, the module-level auxiliary importance is updated with the implicit gradient from a small developing dataset. Extensive experiments show that our proposed MAOAL method consistently outperforms state-of-the-art baselines for different auxiliary losses on various datasets, demonstrating that our method can serve as a powerful generic tool for auxiliary learning.
AAAI Conference 2022 Conference Paper
Modal regression, a widely used regression protocol, has been extensively investigated in statistical and machine learning communities due to its robustness to outliers and heavy-tailed noises. Understanding modal regression’s theoretical behavior can be fundamental in learning theory. Despite significant progress in characterizing its statistical property, the majority of the results are based on the assumption that samples are independent and identical distributed (i. i. d.), which is too restrictive for real-world applications. This paper concerns the statistical property of regularized modal regression (RMR) within an important dependence structure - Markov dependent. Specifically, we establish the upper bound for RMR estimator under moderate conditions and give an explicit learning rate. Our results show that the Markov dependence impacts on the generalization error in the way that sample size would be discounted by a multiplicative factor depending on the spectral gap of underlying Markov chain. This result shed a new light on characterizing the theoretical underpinning for robust regression.
AAAI Conference 2021 Conference Paper
Visual storytelling is a task of generating relevant and interesting stories for given image sequences. In this work we aim at increasing the diversity of the generated stories while preserving the informative content from the images. We propose to foster the diversity and informativeness of a generated story by using a concept selection module that suggests a set of concept candidates. Then, we utilize a large scale pretrained model to convert concepts and images into full stories. To enrich the candidate concepts, a commonsense knowledge graph is created for each image sequence from which the concept candidates are proposed. To obtain appropriate concepts from the graph, we propose two novel modules that consider the correlation among candidate concepts and the image-concept correlation. Extensive automatic and human evaluation results demonstrate that our model can produce reasonable concepts. This enables our model to outperform the previous models by a large margin on the diversity and informativeness of the story, while retaining the relevance of the story to the image sequence.
NeurIPS Conference 2021 Conference Paper
Learning disentangled representations for user intentions from multi-feedback (i. e. , positive and negative feedback) can enhance the accuracy and explainability of recommendation algorithms. However, learning such disentangled representations from multi-feedback data is challenging because i) multi-feedback is complex: there exist complex relations among different types of feedback (e. g. , click, unclick, and dislike, etc) as well as various user intentions, and ii) multi-feedback is noisy: there exists noisy (useless) information both in features and labels, which may deteriorate the recommendation performance. Existing works on disentangled representation learning only focus on positive feedback, failing to handle the complex relations and noise hidden in multi-feedback data. To solve this problem, in this work we propose a Curriculum Disentangled Recommendation (CDR) model that is capable of efficiently learning disentangled representations from complex and noisy multi-feedback for better recommendation. Concretely, we design a co-filtering dynamic routing mechanism that simultaneously captures the complex relations among different behavioral feedback and user intentions as well as denoise the representations in the feature level. We then present an adjustable self-evaluating curriculum that is able to evaluate sample difficulties for better model training and conduct denoising in the label level via disregarding useless information. Our extensive experiments on several real-world datasets demonstrate that the proposed CDR model can significantly outperform several state-of-the-art methods in terms of recommendation accuracy.
AAAI Conference 2021 Conference Paper
Learning theory of distributed algorithms has recently attracted enormous attention in the machine learning community. However, most of existing works focus on learning problem with pointwise loss and does not consider the communication among local processors. In this paper, we propose a new distributed pairwise ranking with communication (called DLSRank-C) based on the Newton-Raphson iteration, and establish its learning rate analysis in probability. Theoretical and empirical assessments demonstrate the effectiveness of DLSRank-C under mild conditions.
AAAI Conference 2021 Conference Paper
Federated Learning (FL) is a promising machine learning paradigm that enables the analyzer to train a model without collecting users’ raw data. To ensure users’ privacy, differentially private federated learning has been intensively studied. The existing works are mainly based on the curator model or local model of differential privacy. However, both of them have pros and cons. The curator model allows greater accuracy but requires a trusted analyzer. In the local model where users randomize local data before sending them to the analyzer, a trusted analyzer is not required but the accuracy is limited. In this work, by leveraging the privacy amplification effect in the recently proposed shuffle model of differential privacy, we achieve the best of two worlds, i. e. , accuracy in the curator model and strong privacy without relying on any trusted party. We first propose an FL framework in the shuffle model and a simple protocol (SS-Simple) extended from existing work. We find that SS-Simple only provides an insufficient privacy amplification effect in FL since the dimension of the model parameter is quite large. To solve this challenge, we propose an enhanced protocol (SS-Double) to increase the privacy amplification effect by subsampling. Furthermore, for boosting the utility when the model size is greater than the user population, we propose an advanced protocol (SS-Topk) with gradient sparsification techniques. We also provide theoretical analysis and numerical evaluations of the privacy amplification of the proposed protocols. Experiments on realworld dataset validate that SS-Topk improves the testing accuracy by 60. 7% than the local model based FL. We highlight an observation that SS-Topk improves the accuracy by 33. 94% than the curator model based FL without any trusted party. Compared with non-private FL, our protocol SS-Topk only lose 1. 48% accuracy under (2. 348, 5e−6 )-DP per epoch.
YNICL Journal 2021 Journal Article
Previous neuroimaging research of eating disorders such as anorexia nervosa and bulimia nervosa has mainly focused on clinical patients, indicating the crucial role of intrinsic connectivity networks involved in aberrant behavioral control (i.e., executive control network), reward reactivity (i.e., basal ganglia network), and excessive self-focused and body-focused ruminations (i.e., default mode network) in the onset and maintenance of eating disturbances. However, examinations of large-scale resting-state networks that support the role of cognitive control, reward sensitivity, and self-directed thinking in disordered eating have rarely involved non-clinical samples from the general population. This study, involving a total of 693 healthy young adults (68.69% females; mean age, 18.37 years), investigated these issues by using pre-defined functional regions of interest from the executive control network, basal ganglia network, default mode network, and a seed-based region of interest-to-region of interest approach. After statistically controlling for differences in age, sex, body mass index, and head motion, we observed significant associations of higher levels of eating disorder symptoms, especially bulimia-type eating (i.e., binge eating and a combination of binge eating and compensatory behaviors, such as purging via self-induced vomiting or laxative use, and compulsive exercise), with weaker intra-network and inter-network functional synchrony. These results remained significant after excluding underweight, overweight, and obese participants. These findings suggest that these neural circuits may play a key role in the symptoms of disordered eating in healthy adults. They further reveal that the less efficient information exchange within and between intrinsic networks associated with self-referential thinking, inhibitory control, and reward sensitivity are strongly related to eating disorder symptoms.
IJCAI Conference 2020 Conference Paper
Knowledge graph alignment aims to link equivalent entities across different knowledge graphs. To utilize both the graph structures and the side information such as name, description and attributes, most of the works propagate the side information especially names through linked entities by graph neural networks. However, due to the heterogeneity of different knowledge graphs, the alignment accuracy will be suffered from aggregating different neighbors. This work presents an interaction model to only leverage the side information. Instead of aggregating neighbors, we compute the interactions between neighbors which can capture fine-grained matches of neighbors. Similarly, the interactions of attributes are also modeled. Experimental results show that our model significantly outperforms the best state-of-the-art methods by 1. 9-9. 7% in terms of HitRatio@1 on the dataset DBP15K.
NeurIPS Conference 2020 Conference Paper
Additive models have attracted much attention for high-dimensional regression estimation and variable selection. However, the existing models are usually limited to the single-task learning framework under the mean squared error (MSE) criterion, where the utilization of variable structure depends heavily on priori knowledge among variables. For high-dimensional observations in real environment, e. g. , Coronal Mass Ejections (CMEs) data, the learning performance of previous methods may be degraded seriously due to the complex non-Gaussian noise and the insufficiency of prior knowledge on variable structure. To tackle this problem, we propose a new class of additive models, called Multi-task Additive Models (MAM), by integrating the mode-induced metric, the structure-based regularizer, and additive hypothesis spaces into a bilevel optimization framework. Our approach does not require any priori knowledge of variable structure and suits for high-dimensional data with complex noise, e. g. , skewed noise, heavy-tailed noise, and outliers. A smooth iterative optimization algorithm with convergence guarantees is provided to implement MAM efficiently. Experiments on simulations and the CMEs analysis demonstrate the competitive performance of our approach for robust estimation and automatic structure discovery.
IJCAI Conference 2019 Conference Paper
Vehicle detection and recognition in remote sensing images are challenging, especially when only limited training data are available to accommodate various target categories. In this paper, we introduce a novel coarse-to-fine framework, which decomposes vehicle detection into segmentation-based vehicle localization and generalized zero-shot vehicle classification. Particularly, the proposed framework can well handle the problem of generalized zero-shot vehicle detection, which is challenging due to the requirement of recognizing vehicles that are even unseen during training. Specifically, a hierarchical DeepLab v3 model is proposed in the framework, which fully exploits fine-grained features to locate the target on a pixel-wise level, then recognizes vehicles in a coarse-grained manner. Additionally, the hierarchical DeepLab v3 model is beneficially compatible to combine the generalized zero-shot recognition. To the best of our knowledge, there is no publically available dataset to test comparative methods, we therefore construct a new dataset to fill this gap of evaluation. The experimental results show that the proposed framework yields promising results on the imperative yet difficult task of zero-shot vehicle detection and recognition.
AAAI Conference 2019 Conference Paper
The proliferation of massive open online courses (MOOCs) demands an effective way of personalized course recommendation. The recent attention-based recommendation models can distinguish the effects of different historical courses when recommending different target courses. However, when a user has interests in many different courses, the attention mechanism will perform poorly as the effects of the contributing courses are diluted by diverse historical courses. To address such a challenge, we propose a hierarchical reinforcement learning algorithm to revise the user profiles and tune the course recommendation model on the revised profiles. Systematically, we evaluate the proposed model on a real dataset consisting of 1, 302 courses, 82, 535 users and 458, 454 user enrolled behaviors, which were collected from XuetangX—one of the largest MOOCs in China. Experimental results show that the proposed model significantly outperforms the state-of-the-art recommendation models (improving 5. 02% to 18. 95% in terms of HR@10).
YNICL Journal 2018 Journal Article
Background and purpose: To investigate effects of radiotherapy on normal brain tissue using in vivo neuroimaging in patients with nasopharyngeal carcinoma (NPC). Methods and materials: < 0.05, which was corrected for multiple comparisons. Results: Volumes of the gray matter, and bilateral temporal lobes decreased in a time-dependent manner, whereas ventricle volume showed a time-dependent increase after radiotherapy. No volume changes were detected in NPC patients before radiotherapy when compared normal controls. No volume changes were detected in the subcohort of patients after completion of induction chemotherapy but prior to initiation of radiotherapy. Changes of bilateral temporal lobe volume correlated with irradiation dose in this region. Expansion of the ventricles correlated with a reduction in cognition assessment. Conclusions: We detected significant and progressive radiotherapy-associated structural changes in the brains of patients with NPC who were treated with standard radiotherapy, especially in the bilateral temporal lobe in which the effect was dose-dependent. Expansion of the ventricles can serve as an imaging marker for treatment-related reduction in cognitive function. Future studies with longer follow-ups are needed to evaluate morphometric changes long-term after radiotherapy.
NeurIPS Conference 2017 Conference Paper
A family of learning algorithms generated from additive models have attracted much attention recently for their flexibility and interpretability in high dimensional data analysis. Among them, learning models with grouped variables have shown competitive performance for prediction and variable selection. However, the previous works mainly focus on the least squares regression problem, not the classification task. Thus, it is desired to design the new additive classification model with variable selection capability for many real-world applications which focus on high-dimensional data classification. To address this challenging problem, in this paper, we investigate the classification with group sparse additive models in reproducing kernel Hilbert spaces. A novel classification method, called as \emph{group sparse additive machine} (GroupSAM), is proposed to explore and utilize the structure information among the input variables. Generalization error bound is derived and proved by integrating the sample error analysis with empirical covering numbers and the hypothesis error estimate with the stepping stone technique. Our new bound shows that GroupSAM can achieve a satisfactory learning rate with polynomial decay. Experimental results on synthetic data and seven benchmark datasets consistently show the effectiveness of our new approach.
NeurIPS Conference 2017 Conference Paper
Linear regression models have been successfully used to function estimation and model selection in high-dimensional data analysis. However, most existing methods are built on least squares with the mean square error (MSE) criterion, which are sensitive to outliers and their performance may be degraded for heavy-tailed noise. In this paper, we go beyond this criterion by investigating the regularized modal regression from a statistical learning viewpoint. A new regularized modal regression model is proposed for estimation and variable selection, which is robust to outliers, heavy-tailed noise, and skewed noise. On the theoretical side, we establish the approximation estimate for learning the conditional mode function, the sparsity analysis for variable selection, and the robustness characterization. On the application side, we applied our model to successfully improve the cognitive impairment prediction using the Alzheimer’s Disease Neuroimaging Initiative (ADNI) cohort data.
NeurIPS Conference 2016 Conference Paper
Nystr\"{o}m method has been used successfully to improve the computational efficiency of kernel ridge regression (KRR). Recently, theoretical analysis of Nystr\"{o}m KRR, including generalization bound and convergence rate, has been established based on reproducing kernel Hilbert space (RKHS) associated with the symmetric positive semi-definite kernel. However, in real world applications, RKHS is not always optimal and kernel function is not necessary to be symmetric or positive semi-definite. In this paper, we consider the generalized Nystr\"{o}m kernel regression (GNKR) with $\ell_2$ coefficient regularization, where the kernel just requires the continuity and boundedness. Error analysis is provided to characterize its generalization performance and the column norm sampling is introduced to construct the refined hypothesis space. In particular, the fast learning rate with polynomial decay is reached for the GNKR. Experimental analysis demonstrates the satisfactory performance of GNKR with the column norm sampling.
YNIMG Journal 2013 Journal Article
Resting-state functional Magnetic Resonance Imaging (rsfMRI) is a powerful tool to investigate neurological and psychiatric diseases. Recently, the evidences linking the scaling properties of resting-state activity and the personality have been accumulated. However, it remains unknown whether the personality is associated with the scale-free dynamics of default mode network (DMN) — the most widely studied network in the rsfMRI literatures. To investigate this question, we estimated the Hurst exponent, quantifying long memory of a time-series, in DMN of rsfMRI in 20 healthy individuals. The Hurst exponent in DMN, whether extracted by independent component analysis (ICA) or region of interest (ROI), was significantly associated with the extraversion score of the revised Eysenck Personality Questionnaire. Specifically, longer memory in DMN corresponded to lower extraversion. We provide evidences for an association between individual differences in personality and scaling dynamics in DMN, whose alteration has been previously linked with introspective cognition. This association might arise from the efficiency in online information processing. Our results suggest that personality trait may be reflected by the scaling property of resting-state networks.
YNIMG Journal 2013 Journal Article
The nature of interactions between observing pain in others (other-pain) and subjective pain perception (self-pain) has been debated. To test whether other-pain and self-pain primes increase or decrease responsiveness to complementary self-pain or other-pain targets, two ERP studies were conducted. In Study 1, twenty participants (10 women, 10 men) were exposed to pictures depicting other-pain or other non-painful situations, followed by self-pain or non-nociceptive heat stimulation delivered to the forearm. Significant visual prime×sensory target interactions indicated that compared to other non-painful primes, other-pain visual primes predicted faster reaction times (RTs) and smaller P2 amplitudes in response to self-pain stimuli while responses to self-heat stimuli were not affected by priming images. However, effects of other-pain primes on elevations in intensity ratings were not specific to self-pain and extended to self-heat targets. In Study 2, self-pain and self-heat stimuli were applied to the same participants followed by other-pain and other non-painful visual targets. Similar to the pattern for Study 1, sensory prime×visual target interactions indicated that compared to self-heat primes, self-pain sensory primes predicted marginally faster RTs and smaller P3 amplitudes in response to other-pain targets while responses to other non-painful targets were unaffected by sensory priming stimuli. Again, self-pain primes predicted higher intensity ratings for both target types compared to self-heat primes. Together, findings supported the shared-representation model of pain empathy more strongly than the threat value of pain hypothesis.
TCS Journal 2012 Journal Article
One approach to guarantee the performance of underwater acoustic sensor networks is to deploy multiple Surface-level Gateways (SGs) at the surface. This paper addresses the connected (or survivable) Constrained Surface-level Gateway Placement (C-SGP ) problem for 3-D underwater acoustic sensor networks. Given a set of underwater sensor nodes (USNs) which are floated at different depths to perform collaborative monitoring tasks over a given region, and a set of candidate locations where SGs may be placed, our objective is to place minimum number of SGs at a subset of candidate locations such that it is connected (or k -connected) from any USN to the base station. We first propose a general algorithm for the connected C-SGP problem and prove its approximation ratio. We also give a constant ratio approximation algorithm for the problem. Second, for the survivable C-SGP problem we also propose a general algorithm and prove its approximation ratio. Finally, we give a constant ratio approximation algorithm for the 2-connected C-SGP problem.
ECAI Conference 2004 Conference Paper