Large-scale dynamic weighted directed network (DWDN) is commonly utilized to illustrate the temporal interactions between nodes in numerous applications. Latent factorization of tensors (LFT) is a typical representation learning approach to extract the desired knowledge from a DWDN via low-rank tensor embedding. However, an existing LFT approach requires the target DWDN to be maintained in one central place like a central server, which is becoming unacceptable for users who are getting increasingly privacy-sensitive. To address this vital issue, this paper innovatively proposes a federated latent factorization of tensors (FLFT) model. It can perform accurate and privacy-preserving representation learning to a DWDN based on four-fold ideas: 1) establishing a data-density-oriented federated learning framework to enable different users to efficiently and cooperatively build a shared LFT model with keeping raw data privacy, 2) incorporating the linear biases into the local training of each user to eliminate the personalized biases or local fluctuations, 3) adopting an effective hybrid filling strategy to further protect each user's private interaction information, and 4) designing a customized nonlinear activation function to capture the nonlinear characteristics of users' interactions. Extensive experiments on four DWDNs collected from industrial applications validate that FLFT demonstrates a notable increase in accuracy compared with state-of-the-art federated and non-federated learning approaches in representing a DWDN. The source code of the proposed FLFT model is shared at the following link:https://github.com/wudi1989/FLFT.

The rapid evolution of multimedia technology has revolutionized human perception, paving the way for multi-view learning. However, traditional multi-view learning approaches are tailored for scenarios with fixed data views, falling short of emulating the intricate cognitive procedures of the human brain processing signals sequentially. Our cerebral architecture seamlessly integrates sequential data through intricate feed-forward and feedback mechanisms. In stark contrast, traditional methods struggle to generalize effectively when confronted with data spanning diverse domains, highlighting the need for innovative strategies that can mimic the brain's adaptability and dynamic integration capabilities. In this paper, we propose a bio-neurologically inspired multi-view incremental framework named MVIL aimed at emulating the brain's fine-grained fusion of sequentially arriving views. MVIL lies two fundamental modules: structured Hebbian plasticity and synaptic partition learning. The structured Hebbian plasticity reshapes the structure of weights to express the high correlation between view representations, facilitating a fine-grained fusion of view representations. Moreover, synaptic partition learning is efficient in alleviating drastic changes in weights and also retaining old knowledge by inhibiting partial synapses. These modules bionically play a central role in reinforcing crucial associations between newly acquired information and existing knowledge repositories, thereby enhancing the network's capacity for generalization. Experimental results on six benchmark datasets show MVIL's effectiveness over state-of-the-art methods.

Considering the importance of capturing both global conversational topics and local speaker dependencies for multimodal emotion recognition in conversations, current approaches first utilize sequence models like Transformer to extract global context information, then apply Graph Neural Networks to model local speaker dependencies for local context information extraction, coupled with Graph Contrastive Learning (GCL) to enhance node representation learning. However, this sequential design introduces potential biases: the extracted global context information inevitably influences subsequent processing, compromising the independence and diversity of the original local features; current graph augmentation methods in GCL cannot consider both global and local context information in conversations to evaluate the node importance, hindering the learning of key information. Inspired by the human brain excels at handling complex tasks by efficiently integrating local and global information processing mechanisms, we propose an aligned global-local context fusion framework for sequence-based design to address these problems. This design includes a dual-attention Transformer and a dual-evaluation method for graph augmentation in GCL. The dual-attention Transformer combines global attention for overall context extraction with sliding-window attention for local context capture, both enhanced by spiking neuron dynamics. The dual-evaluation method in GCL comprises global importance evaluation to identify nodes crucial for overall conversation context, and local importance evaluation to detect nodes significant for local semantics, generating augmented graph views that preserve both global and local information. This approach ensures balanced information processing throughout the pipeline, enhancing biological plausibility and achieving superior emotion recognition.

An informative, creative title prefix is memorable, capable of capturing the attention of readers, and significantly enhances the potential for increased citations. In this work, we pioneer the exploration of the significance of title prefixes in academic papers and propose a controllable title prefix generation model based on curriculum learning. Specifically, we introduce a dedicated dataset named TPOA to compensate for the lack of training data for this emerging task. To make the model capture relevant patterns and language structure, we design three title prefix generation tasks (abstract-based, title-based, and title&abstract-based) to train a ByT5 model into a curriculum learning structure as a generator. After that, we fine-tune another ByT5 model on a target style corpora as a discriminator to control the style of the generated title prefix. Through extensive experiments, our proposed model outperforms existing methods on both human evaluation and automatic evaluation, demonstrating its effectiveness.

Dendrites, pivotal in the integration of synaptic input within neurons, constitute a fundamental substrate for the processing of neural information. Recent investigations have unveiled the intricate spiking dynamics exhibited by dendrites, revealing their potential to amplify neural signals and contribute to intricate neural computation. This study delves into the augmentation of neural network expressivity and learning efficiency through the integration of dendritic functionality into spiking networks, with a particular emphasis on pyramidal neurons prevalent in the cerebral cortex. These neurons rely heavily on their dendritic arbors for information integration and modulation, underscoring the significance of dendritic computation in signal representation and processing. We embarked on modeling the activation properties of pyramidal neurons and scrutinized their nonlinear representation capabilities within artificial neural networks, revealing a heightened expressivity capability with fewer neurons. Additionally, we present a spiking neural network model tailored specifically for pyramidal neurons, encompassing biorealistic nonmonotonic dendritic activation profiles and intricate dendritic morphology. Experimental outcomes underscore the enhanced convergence properties and the superior representational capacity exhibited by our model, enriched with dendritic functionality. This research not only advances our understanding of neuroscience-inspired neural network algorithms, but also sheds light on the computational sophistication inherent in dendritic computation within the brain.

Graph contrastive learning plays a crucial role in many fields, such as social network analysis and recommendation, and has become a hot research area in recent years. The key to improving the quality of contrastive learning is to obtain high-quality sample pairs that reflect the structural features of the data more effectively. Existing methods typically sample based on node similarity and can only select negative samples of a fixed difficulty level, leading to issues like false positives and false negatives. This study proposes a novel paradigm called Hardness-aware Negative Sampling Graph Contrastive Learning with LLMs. We outline the criteria that the adaptive hardness sampling method should follow and provide concrete instances. By adaptively selecting negative samples of appropriate hardness during the training process, this method effectively mitigates false negative and false positive problems. Additionally, we leverage large language models to integrate data with supplementary textual attributes. Extensive experiments and analyses demonstrate the superiority and effectiveness of our proposed method.

Xijia Tao, Shuai Zhong, Lei Li, Qi Liu, Lingpeng Kong. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.

Synaptic plasticity plays a critical role in the expression power of brain neural networks. Among diverse plasticity rules, synaptic scaling presents indispensable effects on homeostasis maintenance and synaptic strength regulation. In the current modeling of brain-inspired spiking neural networks (SNN), backpropagation through time is widely adopted because it can achieve high performance using a small number of time steps. Nevertheless, the synaptic scaling mechanism has not yet been well touched. In this work, we propose an experience-dependent adaptive synaptic scaling mechanism (AS-SNN) for spiking neural networks. The learning process has two stages: First, in the forward path, adaptive short-term potentiation or depression is triggered for each synapse according to afferent stimuli intensity accumulated by presynaptic historical neural activities. Second, in the backward path, long-term consolidation is executed through gradient signals regulated by the corresponding scaling factor. This mechanism shapes the pattern selectivity of synapses and the information transfer they mediate. We theoretically prove that the proposed adaptive synaptic scaling function follows a contraction map and finally converges to an expected fixed point, in accordance with state-of-the-art results in three tasks on perturbation resistance, continual learning, and graph learning. Specifically, for the perturbation resistance and continual learning tasks, our approach improves the accuracy on the N-MNIST benchmark over the baseline by 44% and 25%, respectively. An expected firing rate callback and sparse coding can be observed in graph learning. Extensive experiments on ablation study and cost evaluation evidence the effectiveness and efficiency of our nonparametric adaptive scaling method, which demonstrates the great potential of SNN in continual learning and robust learning.

In the field of ancient Chinese text, extracting and analysing temporal and geographic information are crucial for understanding the personal experiences of historical figures, the development of historical events, and the overall historical background. Currently, named entity recognition(NER) strategies such as BERT+CRF are used to extract temporal and geographic information from ancient Chinese text. However, ancient Chinese text covers a vast time span, and the temporal and geographic entities constantly evolve and change, making it difficult to extract these entities from text. This paper proposes a temporal and geographic extraction model for ancient Chinese text, enhanced by time-series external knowledge base. The extraction of proprietary nouns and general structures are divided into two independent networks. An external database is applied to enhance extraction of proprietary nouns and reduce noise for general structure inference. We constructed address trees and chronological tables containing commonly used places and time-related keywords from different periods and collected 12,000 texts spanning 3,000 years for extensive training. Overall, our research highlights the importance of external knowledge base for ancient Chinese NER, and provides new ideas for research in related fields.

In applications related to big data and service computing, dynamic connections tend to be encountered, especially the dynamic data of user-perspective quality-of-service (QoS) in Web services. They are transformed into high-dimensional and incomplete (HDI) tensors which include abundant temporal pattern information. Latent factorization of tensors (LFT) is an extremely efficient and typical approach for extracting such patterns from an HDI tensor. However, current LFT models require the QoS data to be maintained in a central place (e.g., a central server), which is impossible for increasingly privacy-sensitive users. To address this problem, this article creatively designs a federated learning based on latent factorization of tensors (FL-LFT). It builds a data-density-oriented federated learning model to enable isolated users to collaboratively train a global LFT model while protecting users' privacy. Extensive experiments on a QoS dataset collected from the real world verify that FL-LFT shows a remarkable increase in prediction accuracy when compared to state-of-the-art federated learning (FL) approaches.