Discrete Graph Diffusion Models (DGDMs) mark a pivotal advancement in graph generation, effectively preserving sparsity and structural integrity, thereby enhancing the learning of graph data distributions for diverse generative applications. Despite their potential, DGDMs are computationally intensive due to the numerous low-parameter yet high-computation operations, thereby increasing the need of inference acceleration. A promising solution to mitigate this issue is model quantization. However, existing quantization techniques for Image Diffusion Models (IDMs) face limitations in DGDMs due to differing diffusion processes, while Large Language Model (LLM) quantization focuses on reducing memory access latency of loading large parameters, unlike DGDMs, where inference bottlenecks are computations due to smaller model sizes. To fill this gap, we introduce Bit-DGDM, a post-training quantization framework for DGDMs which incorporates two novel ideas: (i) sparse-dense activation quantization sparsely modeling the activation outliers through adaptively selected, data-free thresholds in full-precision and quantizing the remaining to low-bit, and (ii) ill-conditioned low-rank decomposition decomposing the weights into low-rank component enable faster inference and an $\alpha$-sparsity matrix that models outliers. Extensive experiments demonstrate that Bit-DGDM not only reducing the memory usage from the FP32 baseline by up to $2.8\times$ and achieve up to $2.5\times$ speedup, but also achieve comparable performance to ultra-low precision of up to 4-bit.

Hypergraph neural networks (HyperGNNs) show promise in modeling online networks with high-order correlations. Despite notable progress, training these models on large-scale raw hypergraphs entails substantial computational and storage costs, thereby increasing the need of hypergraph size reduction. However, existing size reduction methods primarily capture pairwise association pattern within conventional graphs, making them challenging to adapt to hypergraphs with high-order correlations. To fill this gap, we introduce a novel hypergraph condensation framework, HG-Cond, designed to distill large-scale hypergraphs into compact, synthetic versions while maintaining comparable HyperGNN performance. Within this framework, we develop a Neural Hyperedge Linker to capture the high-order connectivity pattern through variational inference, achieving linear complexity with respect to the number of nodes. Moreover, We propose a multi-aspectual amelioration strategy including a Gradient-Parameter Synergistic Matching objective to holistically refine synthetic hypergraphs by coordinating improvements in node attributes, high-order connectivity, and label distributions. Extensive experiments demonstrate the efficacy of HG-Cond in hypergraph condensation, notably outperforming the original test accuracy on the 20News dataset while concurrently reducing the hypergraph size to a mere 5% of its initial scale. Furthermore, the condensed hypergraphs demonstrate robust cross-architectural generalizability and potential for expediting neural architecture search.

Neural networks have achieved remarkable success across various fields. However, the lack of interpretability limits their practical use, particularly in critical decision-making scenarios. Posthoc interpretability, which provides explanations for pretrained models, is often at risk of fidelity and robustness. This has inspired a rising interest in self-interpretable neural networks (SINNs), which inherently reveal the prediction rationale through model structures. Despite this progress, existing research remains fragmented, relying on intuitive designs tailored to specific tasks. To bridge these efforts and foster a unified framework, we first collect and review existing works on SINNs and provide a structured summary of their methodologies from five key perspectives: attribution-based, function-based, concept-based, prototype-based, and rule-based self-interpretation. We also present concrete, visualized examples of model explanations and discuss their applicability across diverse scenarios, including image, text, graph data, and deep reinforcement learning (DRL). Additionally, we summarize existing evaluation metrics for self-interpretation and identify open challenges in this field, offering insights for future research. To support ongoing developments, we present a publicly accessible resource to track advancements in this domain: https://github.com/yangji721/Awesome-Self-Interpretable-Neural-Network

Graph neural networks have garnered notable attention for effectively processing graph-structured data. Prevalent models prioritize improving in-distribution (IND) data performance, frequently overlooking the risks from potential out-of-distribution (OOD) nodes during training and inference. In real-world graphs, the automated network construction can introduce noisy nodes from unknown distributions. Previous research into OOD node detection, typically referred to as entropy-based methods, calculates OOD measurements from the prediction entropy alongside category classification training. However, the nodes in the graph might not be pre-labeled with specific categories, rendering entropy-based OOD detectors inapplicable in such category-free situations. To tackle this issue, we propose an energy-centric density estimation framework for OOD node detection, referred to as EnergyDef. Within this framework, we introduce an energy-based GNN to compute node energies that act as indicators of node density and reveal the OOD uncertainty of nodes. Importantly, EnergyDef can efficiently identify OOD nodes with low-resource OOD node annotations, achieved by sampling hallucinated nodes via Langevin Dynamics and structure estimation, along with training through Contrastive Divergence. Our comprehensive experiments on real-world datasets substantiate that our framework markedly surpasses state-of-the-art methods in terms of detection quality, even under conditions of scarce or entirely absent OOD node annotations.

Text-to-SQL parsing has attracted substantial attention recently due to its potential to remove barriers for non-expert end users interacting with databases. A key challenge in Text-to-SQL parsing is developing effective encoding mechanisms to capture the complex relationships between question words, database schemas, and their associated connections within the heterogeneous graph structure. Existing approaches typically introduce some useful multi-hop structures manually and then incorporate them into graph neural networks (GNNs) by stacking multiple layers, which (1) ignore the difficult-to-identify but meaningful semantics embedded in the multi-hop reasoning path, and (2) are limited by the expressive capability of GNN to capture long-range dependencies among the heterogeneous graph. To address these shortcomings, we introduce GRL-SQL, a graph reasoning enhanced language model, which innovatively applies structure encoding to capture the dependencies between node pairs, encompassing one-hop, multi-hop and distance information, subsequently enriched through self-attention for enhanced representational power over GNNs. Furthermore, GRL-SQL incorporates an interaction module that enables joint reasoning and fusion over the question-schema representations for enhancing global context modeling. Comprehensive experiments demonstrate the effectiveness and robustness of our proposed GRL-SQL.

Understanding mathematical questions effectively is a crucial task, which can benefit many applications, such as difficulty estimation. Researchers have drawn much attention to designing pre-training models for question representations due to the scarcity of human annotations (e.g., labeling difficulty). However, unlike general free-format texts (e.g., user comments), mathematical questions are generally designed with explicit purposes and mathematical logic, and usually consist of more complex content, such as formulas, and related mathematical knowledge (e.g., Function). Therefore, the problem of holistically representing mathematical questions remains underexplored. To this end, in this paper, we propose a novel contrastive pre-training approach for mathematical question representations, namely QuesCo, which attempts to bring questions with more similar purposes closer. Specifically, we first design two-level question augmentations, including content-level and structure-level, which generate literally diverse question pairs with similar purposes. Then, to fully exploit hierarchical information of knowledge concepts, we propose a knowledge hierarchy-aware rank strategy (KHAR), which ranks the similarities between questions in a fine-grained manner. Next, we adopt a ranking contrastive learning task to optimize our model based on the augmented and ranked questions. We conduct extensive experiments on two real-world mathematical datasets. The experimental results demonstrate the effectiveness of our model.

Recently, graph-based anomaly detection (GAD) has attracted rising attention due to its effectiveness in identifying anomalies in relational and structured data. Unfortunately, the performance of most existing GAD methods suffers from the inherent structural noises of graphs induced by hidden anomalies connected with considerable benign nodes. In this work, we propose SparseGAD, a novel GAD framework that sparsifies the structures of target graphs to effectively reduce noises and collaboratively learns node representations. It then robustly detects anomalies by uncovering the underlying dependency among node pairs in terms of homophily and heterophily, two essential connection properties of GAD. Extensive experiments on real-world datasets of GAD demonstrate that the proposed framework achieves significantly better detection quality compared with the state-of-the-art methods, even when the graph is heavily attacked. Code will be available at https://github.com/KellyGong/SparseGAD.git.

Although pre-trained language models~(PLMs) have recently advanced the research progress in mathematical reasoning, they are not specially designed as a capable multi-task solver, suffering from high cost for multi-task deployment (e.g. a model copy for a task) and inferior performance on complex mathematical problems in practical applications. To address these issues, we propose JiuZhang 2.0, a unified Chinese PLM specially for multi-task mathematical problem solving. Our idea is to maintain a moderate-sized model and employ the cross-task knowledge sharing to improve the model capacity in a multi-task setting. Specially, we construct a Mixture-of-Experts (MoE) architecture for modeling mathematical text, to capture the common mathematical knowledge across tasks. For optimizing the MoE architecture, we design multi-task continual pre-training and multi-task fine-tuning strategies for multi-task adaptation. These training strategies can effectively decompose the knowledge from the task data and establish the cross-task sharing via expert networks. To further improve the general capacity of solving different complex tasks, we leverage large language models (LLMs) as complementary models to iteratively refine the generated solution by our PLM, via in-context learning. Extensive experiments have demonstrated the effectiveness of our model.

In this paper, we study how to continually pretrain language models for improving the understanding of math problems.Specifically, we focus on solving a fundamental challenge in modeling math problems, i.e., how to fuse the semantics of textual description and formulas, which are highly different in essence.To address this issue, we propose a new approach called COMUS to continually pre-train language models for math problem understanding with syntax-aware memory network.In this approach, we first construct the math syntax graph to model the structural semantic information, by combining the parsing trees of the text and formulas, and then design the syntax-aware memory networks to deeply fuse the features from the graph and text.With the help of syntax relations, we can model the interaction between the token from the text and its semantic-related nodes within the formulas, which is helpful to capture fine-grained semantic correlations between texts and formulas.Besides, we devise three continual pre-training tasks to further align and fuse the representations of the text and math syntax graph.Experimental results on four tasks in the math domain demonstrate the effectiveness of our approach.Our code and data are publicly available at the link: https: //github.com/RUCAIBox/COMUS.

This paper aims to advance the mathematical intelligence of machines by presenting the first Chinese mathematical pre-trained language model (PLM) for effectively understanding and representing mathematical problems. Unlike other standard NLP tasks, mathematical texts are difficult to understand, since they involve mathematical terminology, symbols and formulas in the problem statement. Typically, it requires complex mathematical logic and background knowledge for solving mathematical problems.

Junyi Li, Tianyi Tang, Zheng Gong, Lixin Yang, Zhuohao Yu, Zhipeng Chen, Jingyuan Wang, Xin Zhao, Ji-Rong Wen. Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2022.