Si Zhang

Baoyu Jing, Si Zhang, Yada Zhu et al.

Time series data appears in a variety of applications such as smart transportation and environmental monitoring. One of the fundamental problems for time series analysis is time series forecasting. Despite the success of recent deep time series forecasting methods, they require sufficient observation of historical values to make accurate forecasting. In other words, the ratio of the output length (or forecasting horizon) to the sum of the input and output lengths should be low enough (e.g., 0.3). As the ratio increases (e.g., to 0.8), the uncertainty for the forecasting accuracy increases significantly. In this paper, we show both theoretically and empirically that the uncertainty could be effectively reduced by retrieving relevant time series as references. In the theoretical analysis, we first quantify the uncertainty and show its connections to the Mean Squared Error (MSE). Then we prove that models with references are easier to learn than models without references since the retrieved references could reduce the uncertainty. To empirically demonstrate the effectiveness of the retrieval based time series forecasting models, we introduce a simple yet effective two-stage method, called ReTime consisting of a relational retrieval and a content synthesis. We also show that ReTime can be easily adapted to the spatial-temporal time series and time series imputation settings. Finally, we evaluate ReTime on real-world datasets to demonstrate its effectiveness.

Weilin Cong, Si Zhang, Jian Kang et al.

Recurrent neural network (RNN) and self-attention mechanism (SAM) are the de facto methods to extract spatial-temporal information for temporal graph learning. Interestingly, we found that although both RNN and SAM could lead to a good performance, in practice neither of them is always necessary. In this paper, we propose GraphMixer, a conceptually and technically simple architecture that consists of three components: (1) a link-encoder that is only based on multi-layer perceptrons (MLP) to summarize the information from temporal links, (2) a node-encoder that is only based on neighbor mean-pooling to summarize node information, and (3) an MLP-based link classifier that performs link prediction based on the outputs of the encoders. Despite its simplicity, GraphMixer attains an outstanding performance on temporal link prediction benchmarks with faster convergence and better generalization performance. These results motivate us to rethink the importance of simpler model architecture.

Hanjia Lyu, Song Jiang, Hanqing Zeng et al.

Text-based recommendation holds a wide range of practical applications due to its versatility, as textual descriptions can represent nearly any type of item. However, directly employing the original item descriptions may not yield optimal recommendation performance due to the lack of comprehensive information to align with user preferences. Recent advances in large language models (LLMs) have showcased their remarkable ability to harness commonsense knowledge and reasoning. In this study, we introduce a novel approach, coined LLM-Rec, which incorporates four distinct prompting strategies of text enrichment for improving personalized text-based recommendations. Our empirical experiments reveal that using LLM-augmented text significantly enhances recommendation quality. Even basic MLP (Multi-Layer Perceptron) models achieve comparable or even better results than complex content-based methods. Notably, the success of LLM-Rec lies in its prompting strategies, which effectively tap into the language model's comprehension of both general and specific item characteristics. This highlights the importance of employing diverse prompts and input augmentation techniques to boost the recommendation effectiveness of LLMs.

Zhichen Zeng, Boxin Du, Si Zhang et al.

Finding node correspondence across networks, namely multi-network alignment, is an essential prerequisite for joint learning on multiple networks. Despite great success in aligning networks in pairs, the literature on multi-network alignment is sparse due to the exponentially growing solution space and lack of high-order discrepancy measures. To fill this gap, we propose a hierarchical multi-marginal optimal transport framework named HOT for multi-network alignment. To handle the large solution space, multiple networks are decomposed into smaller aligned clusters via the fused Gromov-Wasserstein (FGW) barycenter. To depict high-order relationships across multiple networks, the FGW distance is generalized to the multi-marginal setting, based on which networks can be aligned jointly. A fast proximal point method is further developed with guaranteed convergence to a local optimum. Extensive experiments and analysis show that our proposed HOT achieves significant improvements over the state-of-the-art in both effectiveness and scalability.

Shuaicheng Zhang, Haohui Wang, Si Zhang et al.

While graph heterophily has been extensively studied in recent years, a fundamental research question largely remains nascent: How and to what extent will graph heterophily affect the prediction performance of graph neural networks (GNNs)? In this paper, we aim to demystify the impact of graph heterophily on GNN spectral filters. Our theoretical results show that it is essential to design adaptive polynomial filters that adapts different degrees of graph heterophily to guarantee the generalization performance of GNNs. Inspired by our theoretical findings, we propose a simple yet powerful GNN named GPatcher by leveraging the MLP-Mixer architectures. Our approach comprises two main components: (1) an adaptive patch extractor function that automatically transforms each node's non-Euclidean graph representations to Euclidean patch representations given different degrees of heterophily, and (2) an efficient patch mixer function that learns salient node representation from both the local context information and the global positional information. Through extensive experiments, the GPatcher model demonstrates outstanding performance on node classification compared with popular homophily GNNs and state-of-the-art heterophily GNNs.

Dongqi Fu, Zhigang Hua, Yan Xie et al.

Graph transformer has been proven as an effective graph learning method for its adoption of attention mechanism that is capable of capturing expressive representations from complex topological and feature information of graphs. Graph transformer conventionally performs dense attention (or global attention) for every pair of nodes to learn node representation vectors, resulting in quadratic computational costs that are unaffordable for large-scale graph data. Therefore, mini-batch training for graph transformers is a promising direction, but limited samples in each mini-batch can not support effective dense attention to encode informative representations. Facing this bottleneck, (1) we start by assigning each node a token list that is sampled by personalized PageRank (PPR) and then apply standard multi-head self-attention only on this list to compute its node representations. This PPR tokenization method decouples model training from complex graph topological information and makes heavy feature engineering offline and independent, such that mini-batch training of graph transformers is possible by loading each node's token list in batches. We further prove this PPR tokenization is viable as a graph convolution network with a fixed polynomial filter and jumping knowledge. However, only using personalized PageRank may limit information carried by a token list, which could not support different graph inductive biases for model training. To this end, (2) we rewire graphs by introducing multiple types of virtual connections through structure- and content-based super nodes that enable PPR tokenization to encode local and global contexts, long-range interaction, and heterophilous information into each node's token list, and then formalize our Virtual Connection Ranking based Graph Transformer (VCR-Graphormer).

Jing Guo, Nan Li, Jianchuan Qi et al.

Large language models (LLMs) have achieved impressive linguistic capabilities. However, a key limitation persists in their lack of human-like memory faculties. LLMs exhibit constrained memory retention across sequential interactions, hindering complex reasoning. This paper explores the potential of applying cognitive psychology's working memory frameworks, to enhance LLM architecture. The limitations of traditional LLM memory designs are analyzed, including their isolation of distinct dialog episodes and lack of persistent memory links. To address this, an innovative model is proposed incorporating a centralized Working Memory Hub and Episodic Buffer access to retain memories across episodes. This architecture aims to provide greater continuity for nuanced contextual reasoning during intricate tasks and collaborative scenarios. While promising, further research is required into optimizing episodic memory encoding, storage, prioritization, retrieval, and security. Overall, this paper provides a strategic blueprint for developing LLM agents with more sophisticated, human-like memory capabilities, highlighting memory mechanisms as a vital frontier in artificial general intelligence.

Limei Wang, Kaveh Hassani, Si Zhang et al.

Transformers serve as the backbone architectures of Foundational Models, where domain-specific tokenizers allow them to adapt to various domains. Graph Transformers (GTs) have recently emerged as leading models in geometric deep learning, outperforming Graph Neural Networks (GNNs) in various graph learning tasks. However, the development of tokenizers for graphs has lagged behind other modalities. To address this, we introduce GQT (\textbf{G}raph \textbf{Q}uantized \textbf{T}okenizer), which decouples tokenizer training from Transformer training by leveraging multi-task graph self-supervised learning, yielding robust and generalizable graph tokens. Furthermore, the GQT utilizes Residual Vector Quantization (RVQ) to learn hierarchical discrete tokens, resulting in significantly reduced memory requirements and improved generalization capabilities. By combining the GQT with token modulation, a Transformer encoder achieves state-of-the-art performance on 20 out of 22 benchmarks, including large-scale homophilic and heterophilic datasets.

Shuaicheng Zhang, Haohui Wang, Junhong Lin et al.

Graph heterophily, where connected nodes have different labels, has attracted significant interest recently. Most existing works adopt a simplified approach - using low-pass filters for homophilic graphs and high-pass filters for heterophilic graphs. However, we discover that the relationship between graph heterophily and spectral filters is more complex - the optimal filter response varies across frequency components and does not follow a strict monotonic correlation with heterophily degree. This finding challenges conventional fixed filter designs and suggests the need for adaptive filtering to preserve expressiveness in graph embeddings. Formally, natural questions arise: Given a heterophilic graph G, how and to what extent will the varying heterophily degree of G affect the performance of GNNs? How can we design adaptive filters to fit those varying heterophilic connections? Our theoretical analysis reveals that the average frequency response of GNNs and graph heterophily degree do not follow a strict monotonic correlation, necessitating adaptive graph filters to guarantee good generalization performance. Hence, we propose [METHOD NAME], a simple yet powerful GNN, which extracts information across the heterophily spectrum and combines salient representations through adaptive mixing. [METHOD NAME]'s superior performance achieves up to 9.2% accuracy improvement over leading baselines across homophilic and heterophilic graphs.

Mufei Li, Dongqi Fu, Limei Wang et al. · gatech

Modern long-context large language models (LLMs) perform well on synthetic "needle-in-a-haystack" (NIAH) benchmarks, but such tests overlook how noisy contexts arise from biased retrieval and agentic workflows. We argue that haystack engineering is necessary to construct noisy long contexts that faithfully capture key real-world factors -- distraction from heterogeneous biased retrievers and cascading errors in agentic workflows -- to test models' long-context robustness. We instantiate it through HaystackCraft, a new NIAH benchmark built on the full English Wikipedia hyperlink network with multi-hop questions. HaystackCraft evaluates how heterogeneous retrieval strategies (e.g., sparse, dense, hybrid, and graph-based) affect distractor composition, haystack ordering, and downstream LLM performance. HaystackCraft further extends NIAH to dynamic, LLM-dependent settings that simulate agentic operations, where models refine queries, reflect on their past reasonings, and decide when to stop. Experiments with 15 long-context models show that (1) while stronger dense retrievers can introduce more challenging distractors, graph-based reranking simultaneously improves retrieval effectiveness and mitigates more harmful distractors; (2) in agentic tests, even advanced models like Gemini 2.5 Pro and GPT-5 suffer cascading failures from self-generated distractors or struggle to perform early stops. These results highlight persistent challenges in agentic long-context reasoning and establish HaystackCraft as a valuable testbed for future progress.

Jialong Han, Si Zhang, Ke Zhang

Parameter-Efficient Fine-Tuning (PEFT) has emerged as a critical paradigm for adapting Large Language Models (LLMs) to downstream tasks, among which Low-rank Adaptation (LoRA) represents one of the most widely adopted methodologies. However, existing LoRA-based approaches exhibit two fundamental limitations: unstable training dynamics and inefficient knowledge transfer from pre-trained models, both stemming from random initialization of adapter parameters. To overcome these challenges, we propose DuDe, a novel approach that decomposes weight matrices into magnitude and direction components, employing Singular Value Decomposition (SVD) for principled initialization. Our comprehensive evaluation demonstrates DuDe's superior performance and robustness, achieving up to 48.35\% accuracy on MMLU and 62.53\% ($\pm$ 1.59) accuracy on GSM8K. Our theoretical analysis and empirical validation collectively demonstrate that DuDe's decomposition strategy enhances optimization stability and better preserves pre-trained representations, particularly for domain-specific tasks requiring specialized knowledge. The combination of robust empirical performance and rigorous theoretical foundations establishes DuDe as a significant contribution to PEFT methodologies for LLMs.

Jialong Han, Si Zhang, Ke Zhang

Fine-tuning Large Language Models (LLMs) has become increasingly challenging due to their massive scale and associated computational costs. Parameter-Efficient Fine-Tuning (PEFT) methodologies have been proposed as computational alternatives; however, their implementations still require significant resources. In this paper, we present OSoRA (Output-Dimension and Singular-Value Initialized Low-Rank Adaptation), a novel PEFT method for LLMs. OSoRA extends Low-Rank Adaptation (LoRA) by integrating Singular Value Decomposition (SVD) with learnable scaling vectors in a unified framework. It first performs an SVD of pre-trained weight matrices, then optimizes an output-dimension vector during training, while keeping the corresponding singular vector matrices frozen. OSoRA substantially reduces computational resource requirements by minimizing the number of trainable parameters during fine-tuning. Comprehensive evaluations across mathematical reasoning, common sense reasoning, and other benchmarks demonstrate that OSoRA achieves comparable or superior performance to state-of-the-art methods like LoRA and VeRA, while maintaining a linear parameter scaling even as the rank increases to higher dimensions. Our ablation studies further confirm that jointly training both the singular values and the output-dimension vector is critical for optimal performance.

Si Zhang, Philip W. L. Fong

This paper proposes a computational model for policy administration. As an organization evolves, new users and resources are gradually placed under the mediation of the access control model. Each time such new entities are added, the policy administrator must deliberate on how the access control policy shall be revised to reflect the new reality. A well-designed access control model must anticipate such changes so that the administration cost does not become prohibitive when the organization scales up. Unfortunately, past Access Control research does not offer a formal way to quantify the cost of policy administration. In this work, we propose to model ongoing policy administration in an active learning framework. Administration cost can be quantified in terms of query complexity. We demonstrate the utility of this approach by applying it to the evolution of protection domains. We also modelled different policy administration strategies in our framework. This allowed us to formally demonstrate that domain-based policies have a cost advantage over access control matrices because of the use of heuristic reasoning when the policy evolves. To the best of our knowledge, this is the first work to employ an active learning framework to study the cost of policy deliberation and demonstrate the cost advantage of heuristic policy administration.

Haohui Wang, Baoyu Jing, Kaize Ding et al.

In the context of long-tail classification on graphs, the vast majority of existing work primarily revolves around the development of model debiasing strategies, intending to mitigate class imbalances and enhance the overall performance. Despite the notable success, there is very limited literature that provides a theoretical tool for characterizing the behaviors of long-tail classes in graphs and gaining insight into generalization performance in real-world scenarios. To bridge this gap, we propose a generalization bound for long-tail classification on graphs by formulating the problem in the fashion of multi-task learning, i.e., each task corresponds to the prediction of one particular class. Our theoretical results show that the generalization performance of long-tail classification is dominated by the overall loss range and the task complexity. Building upon the theoretical findings, we propose a novel generic framework HierTail for long-tail classification on graphs. In particular, we start with a hierarchical task grouping module that allows us to assign related tasks into hypertasks and thus control the complexity of the task space; then, we further design a balanced contrastive learning module to adaptively balance the gradients of both head and tail classes to control the loss range across all tasks in a unified fashion. Extensive experiments demonstrate the effectiveness of HierTail in characterizing long-tail classes on real graphs, which achieves up to 12.9% improvement over the leading baseline method in accuracy.

Yiyan Li, Si Zhang, Rongxing Hu et al.

This paper presents a meta-learning based, automatic distribution system load forecasting model selection framework. The framework includes the following processes: feature extraction, candidate model labeling, offline training, and online model recommendation. Using user load forecasting needs as input features, multiple meta-learners are used to rank the available load forecast models based on their forecasting accuracy. Then, a scoring-voting mechanism weights recommendations from each meta-leaner to make the final recommendations. Heterogeneous load forecasting tasks with different temporal and technical requirements at different load aggregation levels are set up to train, validate, and test the performance of the proposed framework. Simulation results demonstrate that the performance of the meta-learning based approach is satisfactory in both seen and unseen forecasting tasks.