Future link prediction is a fundamental challenge in various real-world dynamic systems. To address this, numerous temporal graph neural networks (temporal GNNs) and benchmark datasets have been developed. However, these datasets often feature excessive repeated edges and lack complex sequential dynamics, a key characteristic inherent in many real-world applications such as recommender systems and "Who-To-Follow" on social networks. This oversight has led existing methods to inadvertently downplay the importance of learning sequential dynamics, focusing primarily on predicting repeated edges. In this study, we demonstrate that existing methods, such as GraphMixer and DyGFormer, are inherently incapable of learning simple sequential dynamics, such as "a user who has followed OpenAI and Anthropic is more likely to follow AI at Meta next." Motivated by this issue, we introduce the Temporal Graph Benchmark with Sequential Dynamics (TGB-Seq), a new benchmark carefully curated to minimize repeated edges, challenging models to learn sequential dynamics and generalize to unseen edges. TGB-Seq comprises large real-world datasets spanning diverse domains, including e-commerce interactions, movie ratings, business reviews, social networks, citation networks and web link networks. Benchmarking experiments reveal that current methods usually suffer significant performance degradation and incur substantial training costs on TGB-Seq, posing new challenges and opportunities for future research. TGB-Seq datasets, leaderboards, and example codes are available at https://tgb-seq.github.io/.

Graph Neural Networks (GNNs) play a pivotal role in graph-based tasks for their proficiency in representation learning. Among the various GNN methods, spectral GNNs employing polynomial filters have shown promising performance on tasks involving both homophilous and heterophilous graph structures. However, The scalability of spectral GNNs on large graphs is limited because they learn the polynomial coefficients through multiple forward propagation executions during forward propagation. Existing works have attempted to scale up spectral GNNs by eliminating the linear layers on the input node features, a change that can disrupt end-to-end training, potentially impact performance, and become impractical with high-dimensional input features. To address the above challenges, we propose ''Spectral Graph Neural Networks with Laplacian Sparsification (SGNN-LS)'', a novel graph spectral sparsification method to approximate the propagation patterns of spectral GNNs. We prove that our proposed method generates Laplacian sparsifiers that can approximate both fixed and learnable polynomial filters with theoretical guarantees. Our method allows the application of linear layers on the input node features, enabling end-to-end training as well as the handling of raw text features. We conduct an extensive experimental analysis on datasets spanning various graph scales and properties to demonstrate the superior efficiency and effectiveness of our method. The results show that our method yields superior results in comparison with the corresponding approximated base models, especially on dataset Ogbn-papers100M(111M nodes, 1.6B edges) and MAG-scholar-C (2.8M features).

Due to the proficiency of self-attention mechanisms (SAMs) in capturing dependencies in sequence modeling, several existing dynamic graph neural networks (DGNNs) utilize Transformer architectures with various encoding designs to capture sequential evolutions of dynamic graphs. However, the effectiveness and efficiency of these Transformer-based DGNNs vary significantly, highlighting the importance of properly defining the SAM on dynamic graphs and comprehensively encoding temporal and interactive dynamics without extra complex modules. In this work, we propose TIDFormer, a dynamic graph TransFormer that fully exploits Temporal and Interactive Dynamics in an efficient manner. We clarify and verify the interpretability of our proposed SAM, addressing the open problem of its uninterpretable definitions on dynamic graphs in previous works. To model the temporal and interactive dynamics, respectively, we utilize the calendar-based time partitioning information and extract informative interaction embeddings for both bipartite and non-bipartite graphs using merely the sampled first-order neighbors. In addition, we jointly model temporal and interactive features by capturing potential changes in historical interaction patterns through a simple decomposition. We conduct extensive experiments on several dynamic graph datasets to verify the effectiveness and efficiency of TIDFormer. The experimental results demonstrate that TIDFormer excels, outperforming state-of-the-art models across most datasets and experimental settings. Furthermore, TIDFormer exhibits significant efficiency advantages compared to previous Transformer-based methods.

Future link prediction on temporal graphs is a fundamental task with wide applicability in real-world dynamic systems. These scenarios often involve both recurring (seen) and novel (unseen) interactions, requiring models to generalize effectively across both types of edges. However, existing methods typically rely on complex memory and aggregation modules, yet struggle to handle unseen edges. In this paper, we revisit the architecture of existing temporal graph models and identify two essential but overlooked modeling requirements for future link prediction: representing nodes with unique identifiers and performing target-aware matching between source and destination nodes. To this end, we propose Cross-Attention based Future Link Predictor on Temporal Graphs (CRAFT), a simple yet effective architecture that discards memory and aggregation modules and instead builds on two components: learnable node embeddings and cross-attention between the destination and the source's recent interactions. This design provides strong expressive power and enables target-aware modeling of the compatibility between candidate destinations and the source's interaction patterns. Extensive experiments on diverse datasets demonstrate that CRAFT consistently achieves superior performance with high efficiency, making it well-suited for large-scale real-world applications.

Graph Neural Networks (GNNs) have demonstrated remarkable effectiveness in recommendation systems. However, conventional graph-based recommenders, such as LightGCN, require maintaining embeddings of size d for each node, resulting in a parameter complexity of O ( n X d ), where n represents the total number of users and items. This scaling pattern poses significant challenges for deployment on large-scale graphs encountered in real-world applications. To address this scalability limitation, we propose Lighter-X , an efficient and modular framework that can be seamlessly integrated with existing GNN-based recommender architectures. Our approach substantially reduces both parameter size and computational complexity while preserving the theoretical guarantees and empirical performance of the base models, thereby enabling practical deployment at scale. Specifically, we analyze the original structure and inherent redundancy in their parameters, identifying opportunities for optimization. Based on this insight, we propose an efficient compression scheme for the sparse adjacency structure and high-dimensional embedding matrices, achieving a parameter complexity of O ( h X d ), where h >> n. Furthermore, the model is optimized through a decoupled framework, reducing computational complexity during the training process and enhancing scalability. Extensive experiments demonstrate that Lighter-X achieves comparable performance to baseline models with significantly fewer parameters. In particular, on large-scale interaction graphs with millions of edges, we are able to attain even better results with only 1% of the parameter over LightGCN.

Graph Neural Networks (GNNs) have aroused increasing research attention for their effectiveness on graph mining tasks. However, full-batch training methods based on stochastic gradient descent (SGD) require substantial resources since all gradient-required computational processes are stored in the acceleration device. The bottleneck of storage challenges the training of classic GNNs on large-scale datasets within one acceleration device. Meanwhile, message-passing based (spatial) GNN designs usually necessitate the homophily hypothesis of the graph, which easily fails on heterophilous graphs. In this paper, we propose the random walk extension for those message-passing based GNNs, enriching them with spectral powers. We prove that our random walk sampling with appropriate correction coefficients generates an unbiased approximation of the$K$-order polynomial filter matrix, thus promoting the neighborhood aggregation of the central nodes. Node-wise sampling strategy and historical embedding allow the classic models to be trained with mini-batches, which extends the scalability of the basic models. To show the effectiveness of our method, we conduct a thorough experimental analysis on some frequently-used benchmarks with diverse homophily and scale. The empirical results show that our model achieves significant performance improvements in comparison with the corresponding base GNNs and some state-of-the-art baselines in node classification tasks.

Search engines are essential internet services, enabling users to efficiently find the information they need. Session search employs users’ session logs of queries to solve complex retrieval tasks, in which users search multiple times until interested documents are found. Most existing session search models focus on the contextual information within the current search, ignoring the evidence from historical search sessions. Considering the fact that many ongoing retrieval tasks should have already been carried out by other users with a similar intent, we argue that historical sessions with similar intents can help improve the accuracy of the current search task. We propose a novel Similar Session-enhanced Ranking (SSR) model to improve the session search performance using historical sessions with similar intents. Specifically, the candidate historical sessions are matched by query-level and session-level semantic similarity, and then query-level neighbor behaviors are aggregated by a Query-guided GNN (QGNN) while session-level neighbor behaviors are aggregated using the attention mechanism. Finally, we integrate the refined and aggregated historical neighbor information into the current search session. Experimental results on AOL and Tiangong-ST datasets show that our SSR model significantly outperforms the state-of-the-art models.

Electromyogram (EMG) signal has been long used in human-robot interface in literature, especially in the area of rehabilitation. Recent rapid development in artificial intelligence (AI) has provided powerful machine learning tools to better explore the rich information embedded in EMG signals. For our specific application task in this work, i.e. estimate human finger force based on EMG signal, a LightGBM (Gradient Boosting Machine) model has been used. The main contribution of this study is the development of an objective and automatic optimal feature selection algorithm that can minimize the number of features used in the LightGBM model in order to simplify implementation complexity, reduce computation burden and maintain comparable estimation performance to the one with full features. The performance of the LightGBM model with selected optimal features is compared with 4 other popular machine learning models based on a dataset including 45 subjects in order to show the effectiveness of the developed feature selection method.

In this paper, a mind controlled multi-task manipulator based on motor imagery electroencephalogram (EEG) is proposed. Describe the system function first: In the case of only two types of control signal, the implementation of multi-task Manipulator relies on a toggle-confirmation mode of operation: the task is switched when imagining the left-hand movement, and the task is confirmed when the right-hand movement is imagined. In the BCI system, common spatial pattern (CSP) is used for feature extraction, mutual information for feature selection, and linear discriminant analysis (LDA) for pattern classification. The EEG signal is processed and classified into two categories, imagery of left-hand and right-hand movement. In this way, we can achieve the multi-task control of the manipulator under the premise of ensuring the accuracy of EEG recognition.