Khaled Alkilane

From finance and healthcare to transportation and beyond, effective time series modeling underpins a wide range of applications. While transformers have achieved success, their reliance on global context limits scalability for lengthy sequences due to the quadratic increase in computational cost with sequence length. Recent research suggests linear models can achieve comparable performance with lower complexity. However, the heterogeneity and non-stationary characteristics of time series data continue to challenge single models’ ability to capture complex temporal dynamics, especially in long-term forecasting. This paper proposes MixMamba, a novel framework for time series modeling applicable across diverse domains. The framework leverages the content-based reasoning strengths of the Mamba model by integrating it as an expert within a mixture-of-experts (MoE) framework. This framework decomposes modeling into a pool of specialized experts, enabling the model to learn robust representations and capture the full spectrum of patterns present in time series data. Furthermore, a dynamic gating network is introduced within the framework. This network adaptively allocates each data segment to the most suitable expert based on its characteristics. This is crucial in non-stationary time series, as it allows the model to adjust dynamically to temporal changes in the underlying data distribution. To prevent bias towards a limited subset of experts, a load balancing loss function is incorporated. Extensive experiments on benchmark datasets demonstrate the effectiveness and robustness of our proposed method in various time series modeling tasks, including long-term and short-term forecasting, as well as classification.

Accurate traffic prediction is crucial for the development of intelligent transportation systems (ITS) and various smart applications. To achieve this, effectively capturing the complex interplay between spatial and temporal dependencies across traffic nodes is essential. However, existing research often focuses solely on fixed spatial dependencies between neighboring nodes, neglecting the potential influence of distant nodes. This paper addresses these limitations by exploring two key types of relationships among traffic nodes. First, we examine indirect relationships based on similarity, where nodes exhibit similar traffic patterns irrespective of their physical proximity. Second, we investigate direct causal relationships, where traffic conditions at one node are directly influenced by other nodes. Based on these findings, we propose a novel approach named TPSC (Traffic Prediction using nodes Similarity and Causal relations). TPSC incorporates a classifier that utilizes the K-Prototype algorithm to group nodes based on their traffic similarity and nearby points of interest (POIs). Separate models are then trained for each cluster. Our model leverages a spatial module that employs graph convolutional network representation learning alongside transfer entropy to capture causal relationships and dynamic spatial dependencies. Additionally, a temporal module is introduced to capture periodic temporal dependencies across three components: recent patterns, daily patterns, and weekly patterns. Extensive experiments are conducted to evaluate proposed model on four large-scale traffic datasets for multiple traffic characteristics including speed, flow, and travel time. The experimental results demonstrate that TPSC surpasses the performance of the compared baselines, highlighting its superior predictive capabilities in traffic prediction.

Traffic forecasting constitutes a task of great importance in intelligent transport systems. Owing to the non-Euclidean structure of traffic data, the complicated spatial correlations, and the dynamic temporal dependencies, it is challenging to predict traffic accurately. Despite the fact that few prior studies have considered the interconnections between multiple traffic nodes at the same timestep, the majority of studies fail to capture the dependencies among multiple nodes at different timesteps. Furthermore, most existing work generates shallow graphs based solely on the distance between traffic nodes, which limits their representation competence and declines their power in capturing complex correlations. In particular, inspired by the recent breakthroughs in the generative adversarial network (GAN) and the power of the graph convolution network (GCN) in handling non-Euclidean data, this paper puts forward an adversarial multi-graph convolutional neural network model, named TFGAN, to address the abovementioned problems. We integrate the unsupervised model elasticity with the supervision provided by supervised training to help the GAN generator model generates accurate traffic predictions. To improve the representation and model the implicit correlations effectively, multiple GCNs are constructed within the generator based on various perspectives, such as similarity, correlation, and spatial distance. Meanwhile, GRU and self-attention are applied after each graph to capture the dynamic temporal dependencies across nodes. The comprehensive experiments on three different traffic variables (traffic flow, speed, and travel time) using six real-world traffic datasets demonstrate that TFGAN outperforms the related state-of-the-art models and achieves significant results.