Recent work shows that linear models can outperform several transformer models in long-term time-series forecasting (TSF). However, instead of explicitly performing temporal interaction through self-attention, linear models implicitly perform it based on stacked MLP structures, which may be insufficient in capturing the complex temporal dependencies and their performance still has potential for improvement. To this end, we propose a Lightweight Sparse Interaction Network (LSINet) for TSF task. Inspired by the sparsity of self-attention, we propose a Multihead Sparse Interaction Mechanism (MSIM). Different from self-attention, MSIM learns the important connections between time steps through sparsity-induced Bernoulli distribution to capture temporal dependencies for TSF. The sparsity is ensured by the proposed self-adaptive regularization loss. Moreover, we observe the shareability of temporal interactions and propose to perform Shared Interactions Learning (SIL) for MSIM to further enhance efficiency and improve convergence. LSINet is a linear model comprising only MLP structures with low overhead and equipped with explicit temporal interaction mechanisms. Extensive experiments on public datasets show that LSINet achieves both higher accuracy and better efficiency than advanced linear models and transformer models in TSF tasks.

Time series forecasting is important in finance domain. Financial time series (TS) patterns are influenced by both short-term public opinions and medium-/long-term policy and market trends. Hence, processing multi-period inputs becomes crucial for accurate financial time series forecasting (TSF). However, current TSF models either use only single-period input, or lack customized designs for addressing multi-period characteristics. In this paper, we propose a Multi-period Learning Framework (MLF) to enhance financial TSF performance. MLF considers both TSF's accuracy and efficiency requirements. Specifically, we design three new modules to better integrate the multi-period inputs for improving accuracy: (i) Inter-period Redundancy Filtering (IRF), that removes the information redundancy between periods for accurate self-attention modeling, (ii) Learnable Weighted-average Integration (LWI), that effectively integrates multi-period forecasts, (iii) Multi-period self-Adaptive Patching (MAP), that mitigates the bias towards certain periods by setting the same number of patches across all periods. Furthermore, we propose a Patch Squeeze module to reduce the number of patches in self-attention modeling for maximized efficiency. MLF incorporates multiple inputs with varying lengths (periods) to achieve better accuracy and reduces the costs of selecting input lengths during training. The codes and datasets are available at https://github.com/Meteor-Stars/MLF.

Time series forecasting (TSF) is crucial in various fields and has gained extensive research. However, most studies are conducted based on TS data with scale homogeneity. This paper proposes a self-Adaptive Scale-handling (AS) module to improve the performance of forecasting TS with scale heterogeneity. It consists of scale scaling selection and calibrating. We first calculate the priori scale factors of each time variable and then selectively calibrate the priori scale factors through neural networks. Hence, we can improve the performance of TSF algorithms by reducing scale restoration errors. We validate our method in collected industrial fund sales datasets from Ant Fortune and Alipay APP. Our AS module can easily be integrated into popular TSF models.

Handling varying computational resources is a critical issue in modern AI applications. Adaptive deep networks, featuring the dynamic employment of multiple classifier heads among different layers, have been proposed to address classification tasks under varying computing resources. Existing approaches typically utilize the last classifier supported by the available resources for inference, as they believe that the last classifier always performs better across all classes. However, our findings indicate that earlier classifier heads can outperform the last head for certain classes. Based on this observation, we introduce the Collaborative Decision Making (CDM) module, which fuses the multiple classifier heads to enhance the inference performance of adaptive deep networks. CDM incorporates an uncertainty-aware fusion method based on evidential deep learning (EDL), that utilizes the reliability (uncertainty values) from the first c-1 classifiers to improve the c-th classifier' accuracy. We also design a balance term that reduces fusion saturation and unfairness issues caused by EDL constraints to improve the fusion quality of CDM. Finally, a regularized training strategy that uses the last classifier to guide the learning process of early classifiers is proposed to further enhance the CDM module's effect, called the Guided Collaborative Decision Making (GCDM) framework. The experimental evaluation demonstrates the effectiveness of our approaches. Results on ImageNet datasets show CDM and GCDM obtain 0.4% to 2.8% accuracy improvement (under varying computing resources) on popular adaptive networks. The code is available at the link https://github.com/Meteor-Stars/GCDM_AdaptiveNet.

Graph Neural Networks (GNNs) are prone to adversarial attacks and discriminatory biases. The cutting-edge studies usually adopt a perturbation-invariant consistency regularization strategy without considering the inherent prediction uncertainties, which can lead to unsatisfactory overconfidence for incorrect prediction under intent graph topology or node features attacks. Besides, operating on the complete graph structure is biased towards global level graph noise and brings severe computational issues. In this work, we develop a multi-view confidence-calibrated framework, called MCCNIFTY, for unified fair and stable graph representation learning. At its core is a multi-view uncertainty-aware node embedding learning module derived from evidential theory, including an intra-view evidence calibration, an inter-view evidence fusion, and an uncertainty-aware message passing process in a GNN architecture, which simultaneously optimizes for counterfactual fairness and stability at the sub-graph level. Experimental results on three real-world datasets demonstrate that our method is capable of adequately capturing inherent uncertainties while improving the fairness and stability via subgraph-induced multiview confidence calibration.

In long‐term evoluation (LTE) femtocell networks, hysteresis is one of the main parameters which affects the performance of handover with a number of unnecessary handovers, including ping‐pong, early, late and incorrect handovers. In this study, the authors propose a hybrid algorithm that aims to obtain the optimised unique hysteresis for an individual mobile user moving at various speeds during the inbound handover process. This algorithm is proposed for two‐tier scenarios with macro and femto. The centralised function in this study evaluates the overall handover performance indicator. Then, the handover aggregate performance indicator (HAPI) is used to determine an optimal configuration. Based on the received reference signal‐to‐interference‐plus‐noise ratio, the distributed function residing on the user equipment (UE) is able to obtain an optimal unique hysteresis for the individual UE. Theoretical analysis with three indication boundaries is provided to evaluate the proposed algorithm. A system‐level simulation is presented, and the proposed algorithm outperformed the existing approaches in terms of handover failure, call‐drop and redundancy handover ratios and also achieved better overall system performance.

Femtocell has been considered as a promising technology in wireless communications to extend indoor service coverage and enhance overall network capacity. Two-tier networks, where the current cellular networks, i.e., macrocells, overlapped with a large number of randomly distributed femtocells, can potentially bring significant benefits. If femtocell access points (FAPs) operate within the same frequency band as macrocells, the cross-tier interference (CTI) creates a distinct impact on the system performance. This paper studies the uplink (UL) interference at FAP caused by approaching macrocell users (MUEs). It is noted that the CTI is more significant to the closed subscriber group (CSG) femtocells. We propose an incentive mechanism (IM) for CSG femtocells to alleviate the UL interfference from approaching MUEs, thus preventing the femtocell users performance from degrading and protecting the neighbor FAPs that might also suffer from the UL interference. Meanwhile, the macrocell also benefits from the IM, in terms of energy saving and UL spectral efficiency. Simulation results show that close to the ideal performance when no CTI presents can be achieved with IM, demonstrating that the proposed scheme is very effective in dealing with uplink CTI.