arXiv subjects

Philip S Yu

Publications and source records attributed to Philip S Yu.

11 recordsLinked to original sources

arXiv2026

End-to-end Conditional Diffusion for Realistic and Controllable Visual Traffic Scenario Generation

Generating closed-loop traffic scenarios that are both realistic and controllable is crucial for evaluating autonomous driving systems, especially under rare safety-critical interactions. Existing learning-based methods often struggle to balance controllability and realism, offering either limited fine-grained control over traffic behavior or controllable scenarios at the expense of behavioral plausibility. This paper presents E2E-CDiff, an end-to-end conditional diffusion framework for controllable and realistic scenario generation. Conditioned on front-view visual observations, E2E-CDiff jointly denoises future motion states and executable low-level controls for route-interacting background vehicles. This unified state-action generation mitigates the planning-control mismatch in conventional two-stage trajectory-then-controller pipelines. Differentiable guidance further regulates speed, enforces drivable-area compliance, and supports collision-avoidance or collision-seeking behaviors, enabling both naturalistic and safety-critical scenario generation. Experiments on Bench2Drive show that E2E-CDiff achieves a favorable controllability-realism trade-off compared with representative reinforcement- and imitation-learning baselines, while its collision-guided variant induces challenging interactions across multiple autonomous driving systems. E2E-CDiff also performs competitively as a learning-based ego planner, demonstrating the generality of end-to-end state-action diffusion.

cs.RO↗

arXiv2026

Domain-Aware Hierarchical Contrastive Learning for Semi-Supervised Generalization Fault Diagnosis

Fault diagnosis under unseen operating conditions remains highly challenging when labeled data are scarce. Semi-supervised domain generalization fault diagnosis (SSDGFD) provides a practical solution by jointly exploiting labeled and unlabeled source domains. However, existing methods still suffer from two coupled limitations. First, pseudo-labels for unlabeled domains are typically generated primarily from knowledge learned on the labeled source domain, which neglects domain-specific geometric discrepancies and thus induces systematic cross-domain pseudo-label bias. Second, unlabeled samples are commonly handled with a hard accept-or-discard strategy, where rigid thresholding causes imbalanced sample utilization across domains, while hard-label assignment for uncertain samples can easily introduce additional noise. To address these issues, we propose a unified framework termed domain-aware hierarchical contrastive learning (DAHCL) for SSDGFD. Specifically, DAHCL introduces a domain-aware learning (DAL) module to explicitly capture source-domain geometric characteristics and calibrate pseudo-label predictions across heterogeneous source domains, thereby mitigating cross-domain bias in pseudo-label generation. In addition, DAHCL develops a hierarchical contrastive learning (HCL) module that combines dynamic confidence stratification with fuzzy contrastive supervision, enabling uncertain samples to contribute to representation learning without relying on unreliable hard labels. In this way, DAHCL jointly improves the quality of supervision and the utilization of unlabeled samples. Furthermore, to better reflect practical industrial scenarios, we incorporate engineering noise into the SSDGFD evaluation protocol. Extensive experiments on three benchmark datasets demonstrate that...

cs.LG↗

arXiv2026

Figma2Code: Automating Multimodal Design to Code in the Wild

Front-end development constitutes a substantial portion of software engineering, yet converting design mockups into production-ready User Interface (UI) code remains tedious and costly. While recent work has explored automating this process with Multimodal Large Language Models (MLLMs), existing approaches typically rely solely on design images. As a result, they must infer complex UI details from images alone, often leading to degraded results. In real-world development workflows, however, design mockups are usually delivered as Figma files, a widely used tool for front-end design, that embed rich multimodal information (e.g., metadata and assets) essential for generating high-quality UI. To bridge this gap, we introduce Figma2Code, a new task that advances design-to-code into a multimodal setting and aims to automate design-to-code in the wild. Specifically, we collect paired design images and their corresponding metadata files from the Figma community. We then apply a series of processing operations, including rule-based filtering, human- and MLLM-based annotation and screening, and metadata refinement. This process yields 3,055 samples, from which designers curate a balanced dataset of 213 high-quality cases. Using this dataset, we benchmark ten state-of-the-art open-source and proprietary MLLMs. Our results show that while proprietary models achieve superior visual fidelity, they remain limited in layout responsiveness and code maintainability. Further experiments across modalities and ablation studies corroborate this limitation, partly due to models' tendency to directly map primitive visual attributes from Figma metadata.

cs.SE↗

arXiv2026

GraphSB: Boosting Imbalanced Node Classification on Graphs through Structural Balance

Imbalanced node classification is a critical challenge in graph learning, where most existing methods typically utilize Graph Neural Networks (GNNs) to learn node representations. These methods can be broadly categorized into the data-level and the algorithm-level. The former aims to synthesize minority-class nodes to mitigate quantity imbalance, while the latter tries to optimize the learning process to highlight minority classes. However, neither of them addresses the inherently imbalanced graph structure, which is a fundamental factor that incurs majority-class dominance and minority-class assimilation in GNNs. Our theoretical analysis further supports this critical insight. Therefore, we propose GraphSB (Graph Structural Balance), a novel framework that incorporates Structural Balance as a key strategy to address the underlying imbalanced graph structure before node synthesis. Structural Balance performs a two-stage structure optimization: Structure Enhancement that mines hard samples near decision boundaries through dual-view analysis and enhances connectivity for minority classes through adaptive augmentation, and Relation Diffusion that propagates the enhanced minority context while simultaneously capturing higher-order structural dependencies. Thus, GraphSB balances structural distribution before node synthesis, enabling more effective learning in GNNs. Extensive experiments demonstrate that GraphSB significantly outperforms the state-of-the-art methods. More importantly, the proposed Structural Balance can be seamlessly integrated into state-of-the-art methods as a simple plug-and-play module, increasing their accuracy by an average of 4.57%.

cs.LG↗

arXiv2024

Multi-Relational Structural Entropy

Structural Entropy (SE) measures the structural information contained in a graph. Minimizing or maximizing SE helps to reveal or obscure the intrinsic structural patterns underlying graphs in an interpretable manner, finding applications in various tasks driven by networked data. However, SE ignores the heterogeneity inherent in the graph relations, which is ubiquitous in modern networks. In this work, we extend SE to consider heterogeneous relations and propose the first metric for multi-relational graph structural information, namely, Multi-relational Structural Entropy (MrSE). To this end, we first cast SE through the novel lens of the stationary distribution from random surfing, which readily extends to multi-relational networks by considering the choices of both nodes and relation types simultaneously at each step. The resulting MrSE is then optimized by a new greedy algorithm to reveal the essential structures within a multi-relational network. Experimental results highlight that the proposed MrSE offers a more insightful interpretation of the structure of multi-relational graphs compared to SE. Additionally, it enhances the performance of two tasks that involve real-world multi-relational graphs, including node clustering and social event detection.

cs.SI↗

arXiv2023

Mutual Wasserstein Discrepancy Minimization for Sequential Recommendation

Self-supervised sequential recommendation significantly improves recommendation performance by maximizing mutual information with well-designed data augmentations. However, the mutual information estimation is based on the calculation of Kullback Leibler divergence with several limitations, including asymmetrical estimation, the exponential need of the sample size, and training instability. Also, existing data augmentations are mostly stochastic and can potentially break sequential correlations with random modifications. These two issues motivate us to investigate an alternative robust mutual information measurement capable of modeling uncertainty and alleviating KL divergence limitations. To this end, we propose a novel self-supervised learning framework based on Mutual WasserStein discrepancy minimization MStein for the sequential recommendation. We propose the Wasserstein Discrepancy Measurement to measure the mutual information between augmented sequences. Wasserstein Discrepancy Measurement builds upon the 2-Wasserstein distance, which is more robust, more efficient in small batch sizes, and able to model the uncertainty of stochastic augmentation processes. We also propose a novel contrastive learning loss based on Wasserstein Discrepancy Measurement. Extensive experiments on four benchmark datasets demonstrate the effectiveness of MStein over baselines. More quantitative analyses show the robustness against perturbations and training efficiency in batch size. Finally, improvements analysis indicates better representations of popular users or items with significant uncertainty. The source code is at https://github.com/zfan20/MStein.

cs.LG↗

arXiv2022

Time Lag Aware Sequential Recommendation

Although a variety of methods have been proposed for sequential recommendation, it is still far from being well solved partly due to two challenges. First, the existing methods often lack the simultaneous consideration of the global stability and local fluctuation of user preference, which might degrade the learning of a user's current preference. Second, the existing methods often use a scalar based weighting schema to fuse the long-term and short-term preferences, which is too coarse to learn an expressive embedding of current preference. To address the two challenges, we propose a novel model called Time Lag aware Sequential Recommendation (TLSRec), which integrates a hierarchical modeling of user preference and a time lag sensitive fine-grained fusion of the long-term and short-term preferences. TLSRec employs a hierarchical self-attention network to learn users' preference at both global and local time scales, and a neural time gate to adaptively regulate the contributions of the long-term and short-term preferences for the learning of a user's current preference at the aspect level and based on the lag between the current time and the time of the last behavior of a user. The extensive experiments conducted on real datasets verify the effectiveness of TLSRec.

cs.IR↗

arXiv2020

Multi-Task Learning of Generalizable Representations for Video Action Recognition

In classic video action recognition, labels may not contain enough information about the diverse video appearance and dynamics, thus, existing models that are trained under the standard supervised learning paradigm may extract less generalizable features. We evaluate these models under a cross-dataset experiment setting, as the above label bias problem in video analysis is even more prominent across different data sources. We find that using the optical flows as model inputs harms the generalization ability of most video recognition models. Based on these findings, we present a multi-task learning paradigm for video classification. Our key idea is to avoid label bias and improve the generalization ability by taking data as its own supervision or supervising constraints on the data. First, we take the optical flows and the RGB frames by taking them as auxiliary supervisions, and thus naming our model as Reversed Two-Stream Networks (Rev2Net). Further, we collaborate the auxiliary flow prediction task and the frame reconstruction task by introducing a new training objective to Rev2Net, named Decoding Discrepancy Penalty (DDP), which constraints the discrepancy of the multi-task features in a self-supervised manner. Rev2Net is shown to be effective on the classic action recognition task. It specifically shows a strong generalization ability in the cross-dataset experiments.

cs.CV↗

arXiv2019

Memory In Memory: A Predictive Neural Network for Learning Higher-Order Non-Stationarity from Spatiotemporal Dynamics

Natural spatiotemporal processes can be highly non-stationary in many ways, e.g. the low-level non-stationarity such as spatial correlations or temporal dependencies of local pixel values; and the high-level variations such as the accumulation, deformation or dissipation of radar echoes in precipitation forecasting. From Cramer's Decomposition, any non-stationary process can be decomposed into deterministic, time-variant polynomials, plus a zero-mean stochastic term. By applying differencing operations appropriately, we may turn time-variant polynomials into a constant, making the deterministic component predictable. However, most previous recurrent neural networks for spatiotemporal prediction do not use the differential signals effectively, and their relatively simple state transition functions prevent them from learning too complicated variations in spacetime. We propose the Memory In Memory (MIM) networks and corresponding recurrent blocks for this purpose. The MIM blocks exploit the differential signals between adjacent recurrent states to model the non-stationary and approximately stationary properties in spatiotemporal dynamics with two cascaded, self-renewed memory modules. By stacking multiple MIM blocks, we could potentially handle higher-order non-stationarity. The MIM networks achieve the state-of-the-art results on four spatiotemporal prediction tasks across both synthetic and real-world datasets. We believe that the general idea of this work can be potentially applied to other time-series forecasting tasks.

cs.LG↗

arXiv2019

Beyond Frequency: Utility Mining with Varied Item-Specific Minimum Utility

Utility-oriented mining which integrates utility theory and data mining is a useful tool for understanding economic consumer behavior. Traditional algorithms for mining high-utility patterns (HUPs) applies a single/uniform minimum high-utility threshold (minutil) to obtain the set of HUPs, but in some real-life circumstances, some specific products may bring lower utilities compared with others, but their profit may offer some vital information. However, if minutil is set high, the patterns with low minutil are missed; if minutil is set low, the number of patterns becomes unmanageable. In this paper, an efficient one-phase utility-oriented pattern mining algorithm, called HIMU, is proposed for mining HUPs with varied item-specific minimum utility. A novel tree structure called a multiple item utility set-enumeration tree (MIU-tree), the global sorted and the conditional downward closure properties are introduced in HIMU. In addition, we extended the compact utility-list structure to keep the necessary information, and thus this one-phase HIMU model greatly reduces the computational costs and memory requirements. Moreover, two pruning strategies are then extended to enhance the performance. We conducted extensive experiments in several synthetic and real-world datasets; the results indicates that the designed one-phase HIMU algorithm can address the "rare item problem" and has better performance than the state-of-the-art algorithms in terms of runtime, memory usage, and scalability. Furthermore, the enhanced algorithms outperform the non-optimized HIMU approach.

cs.DB↗

arXiv2013

On the Feature Discovery for App Usage Prediction in Smartphones

With the increasing number of mobile Apps developed, they are now closely integrated into daily life. In this paper, we develop a framework to predict mobile Apps that are most likely to be used regarding the current device status of a smartphone. Such an Apps usage prediction framework is a crucial prerequisite for fast App launching, intelligent user experience, and power management of smartphones. By analyzing real App usage log data, we discover two kinds of features: The Explicit Feature (EF) from sensing readings of built-in sensors, and the Implicit Feature (IF) from App usage relations. The IF feature is derived by constructing the proposed App Usage Graph (abbreviated as AUG) that models App usage transitions. In light of AUG, we are able to discover usage relations among Apps. Since users may have different usage behaviors on their smartphones, we further propose one personalized feature selection algorithm. We explore minimum description length (MDL) from the training data and select those features which need less length to describe the training data. The personalized feature selection can successfully reduce the log size and the prediction time. Finally, we adopt the kNN classification model to predict Apps usage. Note that through the features selected by the proposed personalized feature selection algorithm, we only need to keep these features, which in turn reduces the prediction time and avoids the curse of dimensionality when using the kNN classifier. We conduct a comprehensive experimental study based on a real mobile App usage dataset. The results demonstrate the effectiveness of the proposed framework and show the predictive capability for App usage prediction.

cs.LG↗