Hypergraphs have demonstrated their superiority in modeling complex systems compared to traditional graphs by directly capturing the interactions among multiple entities. Hyperedge prediction, which aims to predict unobserved potential hyperedges, is a fundamental task in hypergraph analysis. A critical component in hyperedge prediction is the sampling of informative negative hyperedges from significantly larger candidate negative sets, compared to traditional graphs, to enhance model training efficacy. Most existing methods utilize predefined heuristics to sample negative hyperedges, resulting in limited generalizability due to their reliance on these predefined rules. The new state-of-the-art in this field is generation-based methods, which treat negative sampling as a generative task. Nevertheless, current generation-based approaches are not scalable to large hypergraphs. Additionally, diffusion models have demonstrated superior performance in numerous generative tasks, yet their potential application in the generation of negative hyperedges remains unexplored. However, the adaptation of diffusion models to this specific task presents challenges due to: (1) diffusion models are inherently designed to generate high-quality positive samples, which are well-defined, as opposed to negative samples; (2) diffusion models are traditionally employed in continuous space, whereas negative sampling for hyperedge prediction operates in discrete space.To address these complexities, we introduce SEHP (Scalable and Effective Negative Sample Generation for Hyperedge Prediction), which employs a conditional diffusion model to iteratively generate and refine negative hyperedges, thereby advancing them towards the decision boundary to improve model performance. SEHP further enhances scalability by effectively sampling sub-hypergraphs, integrating global structural information into the diffusion model for batch training. Extensive experiments conducted on real-world datasets demonstrate that SEHP surpasses existing state-of-the-art methods in both prediction accuracy and scalability. The code of our paper is available at https://github.com/SLQu/SEHP.

Hypergraphs as an expressive and general structure have attracted considerable attention from various research domains. Most existing hypergraph node representation learning techniques are based on graph neural networks, and thus adopt the two-stage message passing paradigm (i.e. node → hyperedge → node). This paradigm only focuses on local information propagation and does not effectively take into account global information, resulting in less optimal representations. Our theoretical analysis of representative two-stage message passing methods shows that, mathematically, they model different ways of local message passing through hyperedges, and can be unified into one-stage message passing (i.e. node → node). However, they still only model local information. Motivated by this theoretical analysis, we propose a novel one-stage message passing paradigm to model both global and local information propagation for hypergraphs. We integrate this paradigm into HGraphormer, a Transformer-based framework for hypergraph node representation learning. HGraphormer injects the hypergraph structure information (local information) into Transformers (global information) by combining the attention matrix and hypergraph Laplacian. Extensive experiments demonstrate that HGraphormer outperforms recent hypergraph learning methods on five representative benchmark datasets on the semi-supervised hypernode classification task, setting new state-of-the-art performance, with accuracy improvements between 2.52 % and 6.70 %. Our code and datasets are available. 1

Sociocultural norms serve as guiding principles for personal conduct in social interactions, emphasizing respect, cooperation, and appropriate behavior, which is able to benefit tasks including conversational information retrieval, contextual information retrieval, and retrieval-enhanced machine learning. We propose a scalable approach for constructing a Sociocultural Norm ( Scn ) Base using large language models (LLMs) for socially aware dialogues. We construct a comprehensive and publicly accessible Chinese Sociocultural NormBase ( ChineseNormBase ). Our approach utilizes socially aware dialogues, enriched with contextual frames, as the primary data source to constrain the generating process and reduce the hallucinations. This enables extracting of high-quality and nuanced natural-language norm statements, leveraging the pragmatic implications of utterances with respect to the situation. As real dialogue annotated with gold frames are not readily available, we propose using synthetic data. Our empirical results show (i) the quality of the Scn s derived from synthetic data is comparable to that from real dialogues annotated with gold frames, and (ii) the quality of the Scn s extracted from real data, annotated with either silver (predicted) or gold frames, surpasses that without the frame annotations. We further show the effectiveness of the extracted Scn s in a Retrieval-Augmented Generation (RAG)-based model to reason about multiple downstream dialogue tasks.

Deep models for Multivariate Time Series (MTS) forecasting have recently demonstrated significant success. Channel-dependent models capture complex dependencies that channel-independent models cannot capture. However, the number of channels in real-world applications outpaces the capabilities of existing channel-dependent models, and contrary to common expectations, some models underperform the channel-independent models in handling high-dimensional data, which raises questions about the performance of channel-dependent models. To address this, our study first investigates the reasons behind the suboptimal performance of these channel-dependent models on high-dimensional MTS data. Our analysis reveals that two primary issues lie in the introduced noise from unrelated series that increases the difficulty of capturing the crucial inter-channel dependencies, and challenges in training strategies due to high-dimensional data. To address these issues, we propose STHD, the Scalable Transformer for High-Dimensional Multivariate Time Series Forecasting. STHD has three components: a) Relation Matrix Sparsity that limits the noise introduced and alleviates the memory issue; b) ReIndex applied as a training strategy to enable a more flexible batch size setting and increase the diversity of training data; and c) Transformer that handles 2-D inputs and captures channel dependencies. These components jointly enable STHD to manage the high-dimensional MTS while maintaining computational feasibility. Furthermore, experimental results show STHD's considerable improvement on three high-dimensional datasets: Crime-Chicago, Wiki-People, and Traffic. The source code and dataset are publicly available https://github.com/xinzzzhou/ScalableTransformer4HighDimensionMTSF.git.

Recently, Memory-based Neural Recommenders (MNR) have demonstrated superior predictive accuracy in the task of sequential recommendations, particularly for modeling long-term item dependencies. However, typical MNR requires complex memory access operations, i.e., both writing and reading via a controller (e.g., RNN) at every time step. Those frequent operations will dramatically increase the network training time, resulting in the difficulty in being deployed on industrial-scale recommender systems. In this paper, we present a novel generalChunkframework to accelerate MNR significantly. Specifically, our framework divides proximal information units into chunks, and performs memory access at certain time steps, whereby the number of memory operations can be greatly reduced. We investigate two ways to implement effective chunking, i.e., PEriodic Chunk (PEC) and Time-Sensitive Chunk (TSC), to preserve and recover important recurrent signals in the sequence. Since chunk-accelerated MNR models take into account more proximal information units than that from a single timestep, it can alleviate the influence of noise in the user-item interaction sequence to a large extent, and thus improve the stability of MNR. In this way, the proposed chunk mechanism can lead to not only faster training and prediction, but even slightly better results. The experimental results on three real-world datasets (weishi, ml-10M and ml-latest) show that our chunk framework notably reduces the running time (e.g., with up to 7x for training & 10x for inference on ml-latest) of MNR, and meantime achieves competitive performance.