Time series forecasting underpins many real-world services. Recent trends have focused on foundation models inspired by the paradigm of large language models, which rely on large volumes of centralized time-series data across diverse domains. However, such approaches raise significant concerns regarding data privacy. Federated learning (FL) has emerged as a promising paradigm for training unified time-series models using isolated datasets distributed across multiple clients. Nevertheless, existing FL methods face two critical challenges: heterogeneous variables and heterogeneous temporal correlations. To address these issues, we propose FedRMamba, a personalized federated forecasting framework built entirely from Mamba state-space blocks. Each client adopts a residual-coupled architecture, where a global frequency-aware Mamba module captures the common low-frequency structures shared across different variables, while a local patch-wise Mamba module learns personalized high-frequency patterns within the multivariate context. To clearly separate these responsibilities, we introduce a frequency-aware supervision that aligns the global path with low-frequency components and the local path with high-frequency residuals. Additionally, we design a gated fusion mechanism that dynamically combines the low-frequency and high-frequency components for improved prediction. We conduct extensive experiments to evaluate the performance of our proposed framework, demonstrating its effectiveness in handling heterogeneous data in federated settings.

With the advancement of graph representation learning, self-supervised graph contrastive learning (GCL) has emerged as a key technique in the field. In GCL, positive and negative samples are generated through data augmentation. While recent works have introduced model-based methods to enhance positive graph augmentations, they often overlook the importance of negative samples, relying instead on rule-based methods that can fail to capture meaningful graph patterns. To address this issue, we propose a novel model-based adversarial contrastive graph augmentation (ACGA) method that automatically generates both positive graph samples with minimal sufficient information and hard negative graph samples. Additionally, we provide a theoretical framework to analyze the process of positive and negative graph augmentation in self-supervised GCL. We evaluate our ACGA method through extensive experiments on representative benchmark datasets, and the results demonstrate that ACGA outperforms state-of-the-art baselines.

Federated learning (FL) enables the training of a global machine learning model among multiple local clients in a collaborative fashion without directly sharing the details of their data. Due to this advantage, it has been utilized in a wide range of applications where privacy is a critical concern and has attracted great attention for graph representation learning (GRL). Despite the offered advances, there still exist two major challenges in the FL for GRL across distributed graph data, including heterogeneity and complementarity. In order to tackle these challenges, a novel personalized federated graph augmentation (PFGA) framework is proposed in this work. Unlike existing techniques, it utilizes generative models as bridges to enable information sharing among clients, thereby facilitating the collaborative training of GRL models. Instead of directly using the generative model trained on each client individually, we aggregate them into the globally generative model to gain a global view of the entire graph, which effectively alleviates the heterogeneity and complementarity issues simultaneously. We formulate the training of the generative and GRL models as a min-max adversarial learning problem and theoretically prove the convergence. Furthermore, the effectiveness of the method is demonstrated using experimental results on six real-world datasets.

Traffic signal control plays a pivotal role in the management of urban traffic flow. With the rapid advancement of reinforcement learning, the development of signal control methods has seen a significant boost. However, a major challenge in implementing these methods is ensuring that signal lights do not change abruptly, as this can lead to traffic accidents. To mitigate this risk, a time-delay is introduced in the implementation of control actions, but usually has a negative impact on the overall efficacy of the control policy. To address this challenge, this paper presents a novel Traffic Signal Control Framework (PRLight), which leverages an On-policy Traffic Control Model (OTCM) and an Online Traffic Prediction Model (OTPM) to achieve efficient and real-time control of traffic signals. The framework collects multi-source traffic information from a local-view graph in real-time and employs a novel fast attention mechanism to extract relevant traffic features. To be specific, OTCM utilizes the predicted traffic state as input, eliminating the need for communication with other agents and maximizing computational efficiency while ensuring that the most relevant information is used for signal control. The proposed framework was evaluated on both simulated and real-world road networks and compared to various state-of-the-art methods, demonstrating its effectiveness in preventing traffic congestion and accidents.

Significant progress has been made in graph representation learning in recent years. However, most of these methods model spatial relationships via predefined graphs or decouple spatial-temporal representations, which limits the generalization and effectiveness of the model. To address these issues, we introduce an adaptive multi-graph contrastive transformer (AMGCT) for general spatial-temporal graph representation learning. Specifically, we first propose adaptive multi-graph contrastive learning (AMGCL). Without any expert knowledge, AMGCL can gradually generate adaptive spatial graphs with different topologies to learn spatial representations from different views. Cross-graph contrastive learning further explores potential correlations between different views, making each view's features more discriminative. In addition, to avoid insufficient interaction caused by decoupling spatial-temporal information in existing methods, we design a coupled graph transformer (CGT) to consider spatial relationships at each stage of temporal modeling, explore complementary information between spatial and temporal domains, and obtain more compact spatial-temporal representations. Experimental results on two different spatial-temporal graph datasets and tasks demonstrate that the proposed method achieves excellent performance.

Conversion rate (CVR) prediction is becoming increasingly important in the multi-billion dollar online display advertising industry. It has two major challenges: firstly, the scarce user history data is very complicated and non-linear; secondly, the time delay between the clicks and the corresponding conversions can be very large, e.g., ranging from seconds to weeks. Existing models usually suffer from such scarce and delayed conversion behaviors. In this paper, we propose a novel deep learning framework to tackle the two challenges. Specifically, we extract the pre-trained embedding from impressions/clicks to assist in conversion models and propose an inner/self-attention mechanism to capture the fine-grained personalized product purchase interests from the sequential click data. Besides, to overcome the time-delay issue, we calibrate the delay model by learning dynamic hazard function with the abundant post-click data more in line with the real distribution. Empirical experiments with real-world user behavior data prove the effectiveness of the proposed method.

As huge commercial value of the recommender system, there has been growing interest to improve its performance in recent years. The majority of existing methods have achieved great improvement on the metric of click, but perform poorly on the metric of conversion possibly due to its extremely sparse feedback signal. To track this challenge, we design a novel deep hierarchical reinforcement learning based recommendation framework to model consumers' hierarchical purchase interest. Specifically, the high-level agent catches long-term sparse conversion interest, and automatically sets abstract goals for low-level agent, while the low-level agent follows the abstract goals and catches short-term click interest via interacting with real-time environment. To solve the inherent problem in hierarchical reinforcement learning, we propose a novel multi-goals abstraction based deep hierarchical reinforcement learning algorithm (MaHRL). Our proposed algorithm contains three contributions: 1) the high-level agent generates multiple goals to guide the low-level agent in different sub-periods, which reduces the difficulty of approaching high-level goals; 2) different goals share the same state encoder structure and its parameters, which increases the update frequency of the high-level agent and thus accelerates the convergence of our proposed algorithm; 3) an appreciated reward assignment mechanism is designed to allocate rewards in each goal so as to coordinate different goals in a consistent direction. We evaluate our proposed algorithm based on a real-world e-commerce dataset and validate its effectiveness.

Sponsored Data Plan (SDP) is an emerging pricing model for the wireless data market where the Content Provider (CP) can sponsor the data usage for specific content on behalf of the users. This strategy sheds new light on the data pricing model and receives significant attention from the Internet Service Provider (ISP). However, the existing SDP studies consider traffic price (e.g., sponsorship) as the only factor that affects user decision. The impact of other classic market features, such as the demand for a variety of contents (i.e., love of variety), remains largely unclear. In this paper, we develop a new model to understand the love of variety in the wireless data market under SDPs. Our model has demonstrated that, such variety is important to understand the complex gaming between ISPs, CPs, and users in both short-run and long-run markets. For example, the analysis indicates that the advantage of CPs with higher revenue will be significantly reduced when users have a greater love of variety. Moreover, to help the ISP better adopt the proposed model in the real market, we also develop a practical method to calibrate the related parameters, which can also be applied to quantity the love of variety.

Urban Mobility Models (UMMs) are fundamental tools for estimating the population in urban sites and their spatial movements over time. Most existing UMMs were developed primarily in 2D. However, we argue that people’s movements and living patterns involve 3D space, i.e., buildings, which can heavily affect the accuracy of UMMs. In this article, we for the first time conduct a comprehensive study on the impacts of buildings on human movements and the effect on UMMs. We innovatively capture the impacts by developing a Semi-absorbing Urban Mobility model (SUM) and theoretically prove its properties on its difference from that of previous UMMs. We also show that calibrating our original SUM may need a large number of parameters. As such, we develop two SUM extensions with a substantially reduced number of parameters, making calibration practical. Our evaluation also demonstrates that, as a basis for supporting mobile applications in an intracity and hourly scale, the SUM is far superior to previous UMMs. In a case study, we also show that the performance of the resource allocation scheme in a cellular network substantially improves by using SUM, with a reduction in the packet loss probability of 3.19 times.

Improving the performance of click-through rate (CTR) prediction remains one of the core tasks in online advertising systems. With the rise of deep learning, CTR prediction models with deep networks remarkably enhance model capacities. In deep CTR models, exploiting users' historical data is essential for learning users' behaviors and interests. As existing CTR prediction works neglect the importance of the temporal signals when embed users' historical clicking records, we propose a time-aware attention model which explicitly uses absolute temporal signals for expressing the users' periodic behaviors and relative temporal signals for expressing the temporal relation between items. Besides, we propose a regularized adversarial sampling strategy for negative sampling which eases the classification imbalance of CTR data and can make use of the strong guidance provided by the observed negative CTR samples. The adversarial sampling strategy significantly improves the training efficiency, and can be co-trained with the time-aware attention model seamlessly. Experiments are conducted on real-world CTR datasets from both in-station and out-station advertising places.

In this paper, we develop a new model to study the competition among Content Providers (CPs) under Sponsored Data Plans (SDPs). SDP is an emerging pricing model for the wireless data market where Internet Service Providers (ISPs) allow a CP to compensate the traffic volume of users when users access the contents of this CP. Studies have shown that SDPs create a triple-win situation, where users consume more contents and the revenue of both CPs and ISPs increases. Currently, a main concern of SDPs is on whether SDPs may bring about unfair competition among CPs. Studies have shown that big CPs have an advantage over small CPs. We observe that such conclusions are derived because in all previous models, traffic price is the only factor that affects user decisions. We argue that it is not precise. Nowadays, people conduct a large variety of activities online, and users have an intrinsic demand for a variety of contents. To reflect this, we for the first time characterize the variety demand as an intrinsic parameter of users, and integrate such variety into a new model to help us drive some novel insights into SDPs, especially the competition among CPs. Our model shows that variety matters for understanding SDPs more thoroughly and comprehensively. For example, under SDPs, the advantage of CPs with higher revenue will be significantly reduced if users have a greater love for variety. Overall, our new model leads to a set of completely new results and rectifies some past conclusions.

Network Embedding is the task of learning continuous node representations for networks, which has been shown effective in a variety of tasks such as link prediction and node classification. Most of existing works aim to preserve different network structures and properties in low-dimensional embedding vectors, while neglecting the existence of noisy information in many real-world networks and the overfitting issue in the embedding learning process. Most recently, generative adversarial networks (GANs) based regularization methods are exploited to regularize embedding learning process, which can encourage a global smoothness of embedding vectors. These methods have very complicated architecture and suffer from the well-recognized non-convergence problem of GANs. In this paper, we aim to introduce a more succinct and effective local regularization method, namely adversarial training, to network embedding so as to achieve model robustness and better generalization performance. Firstly, the adversarial training method is applied by defining adversarial perturbations in the embedding space with an adaptive L2 norm constraint that depends on the connectivity pattern of node pairs. Though effective as a regularizer, it suffers from the interpretability issue which may hinder its application in certain real-world scenarios. To improve this strategy, we further propose an interpretable adversarial training method by enforcing the reconstruction of the adversarial examples in the discrete graph domain. These two regularization methods can be applied to many existing embedding models, and we take DeepWalk as the base model for illustration in the paper. Empirical evaluations in both link prediction and node classification demonstrate the effectiveness of the proposed methods.

Recommender systems play a crucial role in mitigating the problem of information overload by suggesting users' personalized items or services. The vast majority of traditional recommender systems consider the recommendation procedure as a static process and make recommendations following a fixed strategy. In this paper, we propose a novel recommender system with the capability of continuously improving its strategies during the interactions with users. We model the sequential interactions between users and a recommender system as a Markov Decision Process (MDP) and leverage Reinforcement Learning (RL) to automatically learn the optimal strategies via recommending trial-and-error items and receiving reinforcements of these items from users' feedback. Users' feedback can be positive and negative and both types of feedback have great potentials to boost recommendations. However, the number of negative feedback is much larger than that of positive one; thus incorporating them simultaneously is challenging since positive feedback could be buried by negative one. In this paper, we develop a novel approach to incorporate them into the proposed deep recommender system (DEERS) framework. The experimental results based on real-world e-commerce data demonstrate the effectiveness of the proposed framework. Further experiments have been conducted to understand the importance of both positive and negative feedback in recommendations.

Recommender systems can mitigate the information overload problem by suggesting users' personalized items. In real-world recommendations such as e-commerce, a typical interaction between the system and its users is - users are recommended a page of items and provide feedback; and then the system recommends a new page of items. To effectively capture such interaction for recommendations, we need to solve two key problems - (1) how to update recommending strategy according to user's real-time feedback, and 2) how to generate a page of items with proper display, which pose tremendous challenges to traditional recommender systems. In this paper, we study the problem of page-wise recommendations aiming to address aforementioned two challenges simultaneously. In particular, we propose a principled approach to jointly generate a set of complementary items and the corresponding strategy to display them in a 2-D page; and propose a novel page-wise recommendation framework based on deep reinforcement learning, DeepPage, which can optimize a page of items with proper display based on real-time feedback from users. The experimental results based on a real-world e-commerce dataset demonstrate the effectiveness of the proposed framework.

Mobile data demand is increasing tremendously, and thus new pricing models are in urgent need. One promising new pricing scheme is the “sponsored data plan”, i.e., end users may enjoy free access to contents from certain content providers, while these content providers will pay ISPs for corresponding traffic consumed by end users. Proven a number of advantages, the sponsored data plan is still in its infancy. In this paper, we explore some potential of further development of this plan. We extend the design space and propose the idea of time-dependent, sponsoring, i.e, content providers can decide when to sponsor how much fractions of traffic. The key intuition is by migrating some traffic consumption from peak to valley times, bandwidth resources can be better utilized. We formulate a game model to study the interactions between the ISP, CPs and users, and derive the optimal sponsoring fractions over various times under this new plan. We show that all parties involved can benefit from this plan, and social welfare increases. We believe our proposal, i.e., time-dependent sponsoring, provides important insights to potential development of the sponsored data plan.

Data traffic demand over the Internet is increasing rapidly, and it is changing the pricing model between Internet service providers (ISPs), content providers (CPs) and end users. One recent pricing proposal is sponsored data plan, i.e., when accessing contents from a particular CP, end users do not need to pay for that volume of traffic consumed, but the CP will sponsor for this data consumption. In this paper, our goal is to understand the rationale behind this new pricing model, as well as its impacts to the wireless data market, in particular, who will benefit and who will be hurt from this scheme. We build a two-class service model to analyze the consumers' traffic demand under the sponsored data plan with consideration of QoS. We use a two-stage Stackelberg game to characterize the interaction between CPs and the ISP and reveal a number of important findings. Our conclusions include: 1) When the ISP's capacity is sufficient, the sponsored data plan benefits consumers and CPs in the short run, but the ISP does not have incentives to further improve its service in the long run. 2) When ISP's capacity is insufficient, the ISP and end users may achieve a win- win trade, while the ISP and CPs always compete for the revenue. 3) The sponsored data plan may enlarge the un- balance in revenue distribution between different CPs; CPs with higher unit income and poorer technology support are more likely to prefer the sponsored data plan.

With the advances of bandwidth-intensive mobile devices, we see severe congestion problems in wireless data networks. Recently, research emerges to solve this problem from a pricing point of view. Time dependent pricing has been introduced, and initial investigations have shown its advantages over the conventional time independent pricing. Nevertheless, much is unknown in how a practical and effective time dependent pricing scheme can be designed. In this paper, we explore the design space of time dependent pricing. In particular, we focus on a number of schemes, e.g., the usage-based scheme, the flat-rate scheme, and a mixture of them which we called a cap scheme. Our findings include: 1) the ISP obtains a higher profit with usage-based (or flat-rate) scheme if the capacity is insufficient (or sufficient); 2) the usage-based scheme usually achieves a higher consumer surplus and more efficient traffic utilization than the flat-rate scheme; and 3) the cap scheme is strongly preferred by the ISP to further increase its revenue. We believe our findings provide important insights for ISPs to design effective pricing schemes.

No abstract available.