Supply chains are integral to global economic stability, yet disruptions can swiftly propagate through interconnected networks, resulting in substantial economic impacts. Accurate and timely inference of supply chain resilience—the capability to maintain core functions during disruptions—is crucial for proactive risk mitigation and robust network design. However, existing approaches lack effective mechanisms to infer supply chain resilience without explicit system dynamics and struggle to represent the higher-order, multi-entity dependencies inherent in supply chain networks. These limitations motivate the definition of a novel problem and the development of targeted modeling solutions. To address these challenges, we formalize a novel problem: Supply Chain Resilience Inference (SCRI), defined as predicting supply chain resilience using hypergraph topology and observed inventory trajectories without explicit dynamic equations. To solve this problem, we propose the Supply Chain Resilience Inference Hypergraph Network (SC-RIHN), a novel hypergraph-based model leveraging set-based encoding and hypergraph message passing to capture multi-party firm-product interactions. Comprehensive experiments demonstrate that SC-RIHN significantly outperforms traditional MLP, representative graph neural network variants, and ResInf baselines across synthetic benchmarks, underscoring its potential for practical, early-warning risk assessment in complex supply chain systems.

Post-training quantization offers an efficient pathway to deploy super-resolution models, yet existing methods treat weight and activation quantization independently, missing their critical interplay. Through controlled experiments on SwinIR, we uncover a striking asymmetry: weight quantization primarily degrades structural similarity, while activation quantization disproportionately affects pixel-level accuracy. This stems from their distinct roles—weights encode learned restoration priors for textures and edges, whereas activations carry input-specific intensity information. Building on this insight, we propose HarmoQ, a unified framework that harmonizes quantization across components through three synergistic steps: structural residual calibration proactively adjusts weights to compensate for activation-induced detail loss, harmonized scale optimization analytically balances quantization difficulty via closed-form solutions, and adaptive boundary refinement iteratively maintains this balance during optimization. Experiments show HarmoQ achieves substantial gains under aggressive compression, outperforming prior art by 0.46 dB on Set5 at 2-bit while delivering 3.2× speedup and 4× memory reduction on A100 GPUs. This work provides the first systematic analysis of weight-activation coupling in super-resolution quantization and establishes a principled solution for efficient high-quality image restoration.

AI training and inference are driving cloud networks toward terabit-per-second (Tbps) bandwidth per server, challenging the scalability and efficiency of today's cloud network architectures. A prevalent design scales bandwidth by stacking monolithic Data Processing Units (DPUs), but this approach tightly couples control and data plane resources, leading to excessive cost, power consumption, and operational complexity. We identify a fundamental control-data plane divergence in AI clouds: while data plane bandwidth demand grows rapidly, control plane demand remains largely flat due to the dominance of elephant flows. As a result, monolithic DPUs become systematically over-provisioned when used as bandwidth scaling primitives.

This letter investigates the problem of direction-of-departure (DOD) and direction-of-arrival (DOA) estimation for non-line-of-sight (NLOS) targets in bistatic multiple-input multiple-output (MIMO) radar systems assisted by an intelligent reflecting surface (IRS). To tackle this issue, we propose a covariance tensor subspace-based algorithm. First, the received data is modeled within a tensor framework to preserve their inherent multi-dimensional spatiotemporal structure. Then, a fourth-order covariance tensor is constructed by computing correlations along the temporal dimension. Using the higher-order singular value decomposition (HOSVD), the signal subspace matrix is derived from this covariance tensor. The receive steering matrix is accurately reconstructed by exploiting the property of the Khatri–Rao product for full-column-rank matrices. Based on the estimated signal subspace and the reconstructed steering matrix, DOD and DOA estimation is efficiently performed via the rotational invariance technique combined with a one-dimensional correlation-based method, which provides automatic parameter pairing. Simulation results validate the superiority and effectiveness of the proposed algorithm in estimating angles.

The rapid densification of 5G deployments and the emergence of 6G-era services demand accurate cellular traffic forecasting across heterogeneous communication modalities at fine spatiotemporal resolutions. Existing approaches primarily rely on numerical time-series analysis and often underutilize contextual information related to urban function, temporal routines, and external events. This paper presents MobileLLM, a dual-pathway framework that integrates numerical spatiotemporal signals with semantic contextual conditioning for multimodal cellular traffic prediction. The numerical pathway encodes historical traffic observations into node-level tokens, while the semantic pathway transforms structured contextual descriptions into text embeddings. These pathways are fused through a partially frozen GPT-2 backbone and a cross-modal decoder, enabling parameter-efficient adaptation while preserving useful pre-trained priors. Rather than using language models for raw numerical regression, our framework uses the semantic pathway to provide context-aware conditioning for numerical forecasting. Comprehensive evaluation on three real-world datasets-Milan, Trentino, and Shanghai-demonstrates consistent performance improvements across SMS, voice call, and Internet traffic prediction. MobileLLM achieves MAE improvements ranging from 0.88% to 32.62% over strong baselines, with particularly pronounced gains for Internet traffic where contextual dependence is strongest. These results show that combining numerical modeling with semantic contextual representations provides a practical and effective direction for next-generation cellular traffic forecasting.

Generalizable Image Super-Resolution aims to enhance model generalization capabilities under unknown degradations. To achieve this goal, the models are expected to focus only on image content-related features instead of overfitting degradations. Recently, numerous approaches such as Dropout and Feature Alignment have been proposed to suppress models' natural tendency to overfit degradations and yield promising results. Nevertheless, these works have assumed that models overfit to all degradation types (e.g., blur, noise, JPEG), while through careful investigations in this paper, we discover that models predominantly overfit to noise, largely attributable to its distinct degradation pattern compared to other degradation types. In this paper, we propose a targeted feature denoising framework, comprising noise detection and denoising modules. Our approach presents a general solution that can be seamlessly integrated with existing super-resolution models without requiring architectural modifications. Our framework demonstrates superior performance compared to previous regularization-based methods across five traditional benchmarks and datasets, encompassing both synthetic and real-world scenarios.

Spatiotemporal neural networks have shown great promise in urban scenarios by effectively capturing temporal and spatial correlations. However, urban environments are constantly evolving, and current model evaluations are often limited to traffic scenarios and use data mainly collected only a few weeks after training period to evaluate model performance. The generalization ability of these models remains largely unexplored. To address this, we propose a Spatiotemporal Out-of-Distribution (ST-OOD) benchmark, which comprises six urban scenario: bike-sharing, 311 services, pedestrian counts, traffic speed, traffic flow, ride-hailing demand, and bike-sharing, each with in-distribution (same year) and out-of-distribution (next years) settings. We extensively evaluate state-of-the-art spatiotemporal models and find that their performance degrades significantly in out-of-distribution settings, with most models performing even worse than a simple Multi-Layer Perceptron (MLP). Our findings suggest that current leading methods tend to over-rely on parameters to overfit training data, which may lead to good performance on in-distribution data but often results in poor generalization. We also investigated whether dropout could mitigate the negative effects of overfitting. Our results showed that a slight dropout rate could significantly improve generalization performance on most datasets, with minimal impact on in-distribution performance. However, balancing in-distribution and out-of-distribution performance remains a challenging problem. We hope that the proposed benchmark will encourage further research on this critical issue.

Deep learning has led to a dramatic leap on Single Image Super-Resolution (SISR) performances in recent years. While most existing work assumes a simple and fixed degradation model (e.g., bicubic downsampling), the research of Blind SR seeks to improve model generalization ability with unknown degradation. Recently, Kong et al. [37] pioneer the investigation of a more suitable training strategy for Blind SR using Dropout [63]. Although such method indeed brings substantial generalization improvements via mitigating overfitting, we argue that Dropout simultaneously introduces undesirable side-effect that compromises model's capacity to faithfully reconstruct fine details. We show both the theoretical and experimental analyses in our paper, and furthermore, we present another easy yet effective training strategy that enhances the generalization ability of the model by simply modulating its first and second-order features statistics. Experimental results have shown that our method could serve as a model-agnostic regularization and outperforms Dropout on seven benchmark datasets including both synthetic and real-world scenarios.

Spatial-temporal (ST) graph modeling, such as traffic speed forecasting and taxi demand prediction, is an important task in deep learning area. However, for the nodes in the graph, their ST patterns can vary greatly in difficulties for modeling, owning to the heterogeneous nature of ST data. We argue that unveiling the nodes to the model in a meaningful order, from easy to complex, can provide performance improvements over traditional training procedure. The idea has its root in Curriculum Learning, which suggests in the early stage of training models can be sensitive to noise and difficult samples. In this paper, we propose ST-Curriculum Dropout, a novel and easy-to-implement strategy for spatial-temporal graph modeling. Specifically, we evaluate the learning difficulty of each node in high-level feature space and drop those difficult ones out to ensure the model only needs to handle fundamental ST relations at the beginning, before gradually moving to hard ones. Our strategy can be applied to any canonical deep learning architecture without extra trainable parameters, and extensive experiments on a wide range of datasets are conducted to illustrate that, by controlling the difficulty level of ST relations as the training progresses, the model is able to capture better representation of the data and thus yields better generalization.

Recent years have witnessed the great potential of attention mechanism in graph representation learning. However, while variants of attention-based GNNs are setting new benchmarks for numerous real-world datasets, recent works have pointed out that their induced attentions are less robust and generalizable against noisy graphs due to lack of direct supervision. In this paper, we present a new framework which utilizes the tool of causality to provide a powerful supervision signal for the learning process of attention functions. Specifically, we estimate the direct causal effect of attention to the final prediction, and then maximize such effect to guide attention attending to more meaningful neighbors. Our method can serve as a plug-and-play module for any canonical attention-based GNNs in an end-to-end fashion. Extensive experiments on a wide range of benchmark datasets illustrated that, by directly supervising attention functions, the model is able to converge faster with a clearer decision boundary, and thus yields better performances.

Recently, forecasting the crowd flows has become an important research topic, and plentiful technologies have achieved good performances. As we all know, the flow at a citywide level is in a mixed state with several basic patterns (e.g., commuting, working, and commercial) caused by the city area functional distributions (e.g., developed commercial areas, educational areas and parks). However, existing technologies have been criticized for their lack of considering the differences in the flow patterns among regions since they want to build only one comprehensive model to learn the mixed flow tensors. Recognizing this limitation, we present a new perspective on flow prediction and propose an explainable framework named ST-ExpertNet, which can adopt every spatial-temporal model and train a set of functional experts devoted to specific flow patterns. Technically, we train a bunch of experts based on the Mixture of Experts (MoE), which guides each expert to specialize in different kinds of flow patterns in sample spaces by using the gating network. We define several criteria, including comprehensiveness, sparsity, and preciseness, to construct the experts for better interpretability and performances. We conduct experiments on a wide range of real-world taxi and bike datasets in Beijing and NYC. The visualizations of the expert's intermediate results demonstrate that our ST-ExpertNet successfully disentangles the city's mixed flow tensors along with the city layout, e.g., the urban ring road structure. Different network architectures, such as ST-ResNet, ConvLSTM, and CNN, have been adopted into our ST-ExpertNet framework for experiments and the results demonstrates the superiority of our framework in both interpretability and performances.

Travel time estimation from GPS trips is of great importance to order duration, ridesharing, taxi dispatching, etc. However, the dense trajectory is not always available due to the limitation of data privacy and acquisition, while the origin-destination (OD) type of data, such as NYC taxi data, NYC bike data, and Capital Bikeshare data, is more accessible. To address this issue, this paper starts to estimate the OD trips travel time combined with the road network. Subsequently, aMulti-taskWeaklySupervisedLearning Framework forTravelTimeEstimation (MWSL-TTE) has been proposed to infer transition probability between roads segments, and the travel time on road segments and intersection simultaneously. Technically, given an OD pair, the transition probability intends to recover the most possible route. And then, the output of travel time is equal to the summation of all segments’ and intersections’ travel time in this route. A novel route recovery function has been proposed to iteratively maximize the current routes’ co-occurrence probability, and minimize the discrepancy between routes’ probability distribution and the inverse distribution of routes’ estimation loss. Moreover, the expected log-likelihood function based on a weakly-supervised framework has been deployed in optimizing the travel time from road segments and intersections concurrently. We conduct experiments on a wide range of real-world taxi datasets in Xi’an and Chengdu and demonstrate our method's effectiveness on route recovery and travel time estimation.

Estimating the travel time of a path is an essential topic for the intelligent transportation system. It serves as the foundation for real-world applications, such as traffic monitoring, route planning, and taxi dispatching. However, building a model for such a data-driven task requires a large amount of users’ travel information, which closely relates to their privacy and, thus, is less likely to be shared. The not independent and identically distributed (Non-IID) trajectory data across data owners also make a predictive model extremely challenging to be personalized if we directly apply federated learning. Finally, previous work on travel time estimation (TTE) does not consider the real-time traffic state of roads, which we argue, can significantly influence the prediction. To address the above challenges, we introduce GOF-TTE for the mobile user group, generative online federated learning framework for TTE, which 1) utilizes the federated learning approach, allowing private data to be kept on client devices while training, and designs the global model as an online generative model shared by all clients to infer the real-time road traffic state and 2) apart from sharing a base model at the server, adapts a fine-tuned personalized model for every client to study their personal driving habits, making up for the residual error made by localized global model prediction. We also employ a simple privacy attack to our framework and implement the differential privacy mechanism to guarantee privacy safety further. Finally, we conduct experiments on two real-world public taxi data sets of DiDi Chengdu and Xi’an. The experimental results demonstrate the effectiveness of our proposed framework.

Aspect-based sentiment analysis aims to determine the sentiment of a specific aspect in the sentence. Most of the previous studies employ attention-based RNN models to capture aspect-dependent features in sentences or model Inter-Aspect Relation (IAR). However, RNN is difficult to parallelize when calculating all the elements in a sequence, and the word-level weight in attention mechanisms may introduce noise. Besides, we observe that the IAR contains inter-aspect syntactic relation and inter-aspect semantic relation, while the latter is overlooked in past IAR modeling studies. In this paper, we propose a new architecture that employs the multi-head attention mechanism to implement the parallel computation of sequence elements and introduce less noise than traditional attention mechanisms and model both relations in IAR. The experimental results on different types of data show that our model consistently outperforms state-of-the-art methods.