Author name cluster

Zijie Pan

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

11 papers

2 author rows

TMLR Journal 2026 Journal Article

Empowering Power Outage Prediction with Spatially Aware Hybrid Graph Neural Networks and Contrastive Learning

Xuyang Shen
Zijie Pan
Diego Cerrai
Xinxuan Zhang
Christopher Colorio
Emmanouil Anagnostou
Dongjin Song

Extreme weather events, such as severe storms, hurricanes, snowstorms, and ice storms, which are exacerbated by climate change, frequently cause widespread power outages. These outages halt industrial operations, impact communities, damage critical infrastructure, profoundly disrupt economies, and have far-reaching effects across various sectors. To mitigate these effects, the University of Connecticut and Eversource Energy Center have developed an outage prediction modeling (OPM) system to provide pre-emptive forecasts for electric distribution networks before such weather events occur. However, existing predictive models in the system do not incorporate the spatial effect of extreme weather events. To this end, we develop Spatially Aware Hybrid Graph Neural Networks (SA-HGNN) with contrastive learning to enhance the OPM predictions for extreme weather-induced power outages. Specifically, we first encode spatial relationships of both static features (e.g., land cover, infrastructure) and event-specific dynamic features (e.g., wind speed, precipitation) via Spatially Aware Hybrid Graph Neural Networks (SA-HGNN). Next, we leverage contrastive learning to handle the imbalance problem associated with different types of extreme weather events and generate location-specific embeddings by minimizing intra-event distances between similar locations while maximizing inter-event distances across all locations. Thorough empirical studies in four utility service territories, i.e., Connecticut, Western Massachusetts, Eastern Massachusetts, and New Hampshire, demonstrate that SA-HGNN can achieve state-of-the-art performance for power outage prediction.

PDF Details

AAAI Conference 2026 Conference Paper

On the Misalignment Between Data Learnability and Forgettability in Machine Unlearning

Zijie Pan
Zuobin Ying
Yajie Wang
Wanlei Zhou

We report a structural mismatch between a data point’s {learnability}—how quickly it improves the loss—and its {forgettability}—how much it anchors the final parameters—an aspect ignored by prior machine unlearning frameworks such as SISA, Fisher-Forget, and influence-based fine-tuning. To make this gap measurable we introduce Unlearning Gradient Sensitivity (UGS), an influence score computable with a single Hutch++ sketch, and derive the Learnability–Forgettability Divergence (LFD), the Jensen–Shannon distance between the model’s learning and forgetting distributions. We prove that UGS dispersion decays exponentially only under explicit regularisation and that LFD converges to zero when its weight grows sub-linearly relative to the UGS term. Building on these findings, we introduce Dual-Aware Training (DAT)—a lightweight regularization method that reduces variability in how easily data points can be forgotten and aligns learning and forgetting behaviors during training. On CIFAR-10, MNIST, and IMDB, DAT maintains the original model accuracy while cutting forgettability divergence in half and significantly lowering the cost of certified unlearning, showing that it’s effective to make models forgettable from the start.

PDF Details DOI

ICLR Conference 2025 Conference Paper

Diffusion2: Dynamic 3D Content Generation via Score Composition of Video and Multi-view Diffusion Models

Zeyu Yang 0004
Zijie Pan
Chun Gu
Li Zhang 0040

Recent advancements in 3D generation are predominantly propelled by improvements in 3D-aware image diffusion models. These models are pretrained on Internet-scale image data and fine-tuned on massive 3D data, offering the capability of producing highly consistent multi-view images. However, due to the scarcity of synchronized multi-view video data, it remains challenging to adapt this paradigm to 4D generation directly. Despite that, the available video and 3D data are adequate for training video and multi-view diffusion models separately that can provide satisfactory dynamic and geometric priors respectively. To take advantage of both, this paper presents Diffusion$^2$, a novel framework for dynamic 3D content creation that reconciles the knowledge about geometric consistency and temporal smoothness from these models to directly sample dense multi-view multi-frame images which can be employed to optimize continuous 4D representation. Specifically, we design a simple yet effective denoising strategy via score composition of pretrained video and multi-view diffusion models based on the probability structure of the target image array. To alleviate the potential conflicts between two heterogeneous scores, we further introduce variance-reducing sampling via interpolated steps, facilitating smooth and stable generation. Owing to the high parallelism of the proposed image generation process and the efficiency of the modern 4D reconstruction pipeline, our framework can generate 4D content within few minutes. Notably, our method circumvents the reliance on expensive and hard-to-scale 4D data, thereby having the potential to benefit from the scaling of the foundation video and multi-view diffusion models. Extensive experiments demonstrate the efficacy of our proposed framework in generating highly seamless and consistent 4D assets under various types of conditions.

Details

EAAI Journal 2025 Journal Article

Harnessing Large Language Models for question answering over complex tables

Jian Lyu
Zuobin Ying
Ning Shi
Jingfeng Xue
Zijie Pan
Weiping Ding
Wanlei Zhou

Complex table question answering requires deriving precise answers to natural language questions by analyzing structurally complex tables, where cells are arbitrarily merged and header locations are flexible. Despite significant advancements in the large language model (LLM) era, current approaches for complex table reasoning suffer from two critical limitations: either (1) directly feeding the entire table into prompts, which introduces irrelevant information, or (2) requiring additional structures (e. g. , graph-based representations) alongside LLMs, thereby incurring unnecessary system complexity. To address these limitations, we propose MaCTab, a Masked language modeling framework that decomposes Complex Table question answering into cloze-style tasks. Specifically, MaCTab employs two modular decomposition strategies: (1) row-/column-wise retrieval and (2) cell-wise retrieval. Both strategies explicitly retrieve answers from serialized complex tables, enabling strong standalone performance. Meanwhile, their confidence-based combination filters low-confidence outputs to yield complementary gains. Comprehensive experiments on the IM-TQA benchmark — a Table Question Answering dataset with Implicit and Multi-typed structures comprising 1, 200 real-world tables from publicly available business documents and 5, 000 questions — demonstrate MaCTab’s effectiveness. MaCTab achieves 96. 8% exact match accuracy, marking a 43. 4% absolute improvement over the previous state-of-the-art (53. 4%), and surpassing the average performance of five trained human annotators (95. 1%) recruited by the dataset authors. This work establishes a hybrid approach that maintains the simplicity of full-table prompting while enabling graph-free information filtering, offering a simple yet effective paradigm for multi-industry applications requiring precise interpretation of complex tabular data.

Details DOI

AAAI Conference 2025 Conference Paper

Personalized Label Inference Attack in Federated Transfer Learning via Contrastive Meta Learning

Hanyu Zhao
Zijie Pan
Yajie Wang
Zuobin Ying
Lei Xu
Yu-an Tan

Federated Transfer Learning (FTL) is a popular approach to solve the problem of heterogeneous feature space and label distribution. Among the mainstream strategies for FTL, parameter decoupling, which balance the impact of a single global model and multiple personalized models under data heterogeneity, has attracted the attention of many researchers. However, few attacks have been proposed to evaluate the privacy risk of FTL. We find that the fine-tuned structures and the gradient update mechanisms of parameter decoupling would be more likely to leak personalized information for the server to infer private labels. Based on our findings, we propose the label inference attack that combines meta classifier with contrastive learning in FTL. Our experiments show that the proposed attack has ability to extract local personalized information from the differences before and after fine-tuning to improve the accuracy of the attack in the absence of a downstream model. Our research can reveal potential privacy risks in FTL and motivate more research on private and secure FTL.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

TS-RAG: Retrieval-Augmented Generation based Time Series Foundation Models are Stronger Zero-Shot Forecaster

Kanghui Ning
Zijie Pan
Yu Liu
Yushan Jiang
James Zhang
Kashif Rasul
Anderson Schneider
Lintao Ma

Large Language Models (LLMs) and Foundation Models (FMs) have recently become prevalent for time series forecasting tasks. While fine-tuning LLMs enables domain adaptation, they often struggle to generalize across diverse and unseen datasets. Moreover, existing Time Series Foundation Models (TSFMs) still face challenges in handling non-stationary dynamics and distribution shifts, largely due to the lack of effective mechanisms for adaptation. To this end, we present TS-RAG, a retrieval-augmented generation framework for time series forecasting that enhances the generalization and interpretability of TSFMs. Specifically, TS-RAG leverages pre-trained time series encoders to retrieve semantically relevant segments from a dedicated knowledge base, enriching the contextual representation of the input query. Furthermore, we propose an Adaptive Retrieval Mixer (ARM) module that dynamically fuses the retrieved patterns with the TSFM's internal representation, improving forecasting accuracy without requiring task-specific fine-tuning. Thorough empirical studies on seven public benchmark datasets demonstrate that TS-RAG achieves state-of-the-art zero-shot forecasting performance, outperforming the existing TSFMs by up to 6. 84\% across diverse domains while also providing desirable interpretability. Our code and data are available at: https: //github. com/UConn-DSIS/TS-RAG.

PDF Details

IJCAI Conference 2024 Conference Paper

Empowering Time Series Analysis with Large Language Models: A Survey

Yushan Jiang
Zijie Pan
Xikun Zhang
Sahil Garg
Anderson Schneider
Yuriy Nevmyvaka
Dongjin Song

Recently, remarkable progress has been made over large language models (LLMs), demonstrating their unprecedented capability in varieties of natural language tasks. However, completely training a large general-purpose model from the scratch is challenging for time series analysis, due to the large volumes and varieties of time series data, as well as the non-stationarity that leads to concept drift impeding continuous model adaptation and re-training. Recent advances have shown that pre-trained LLMs can be exploited to capture complex dependencies in time series data and facilitate various applications. In this survey, we provide a systematic overview of existing methods that leverage LLMs for time series analysis. Specifically, we first state the challenges and motivations of applying language models in the context of time series as well as brief preliminaries of LLMs. Next, we summarize the general pipeline for LLM-based time series analysis, categorize existing methods into different groups (\textit{i. e. }, direct query, tokenization, prompt design, fine-tune, and model integration), and highlight the key ideas within each group. We also discuss the applications of LLMs for both general and spatial-temporal time series data, tailored to specific domains. Finally, we thoroughly discuss future research opportunities to empower time series analysis with LLMs.

PDF Details DOI

ICLR Conference 2024 Conference Paper

Enhancing High-Resolution 3D Generation through Pixel-wise Gradient Clipping

Zijie Pan
Jiachen Lu
Xiatian Zhu
Li Zhang 0040

High-resolution 3D object generation remains a challenging task primarily due to the limited availability of comprehensive annotated training data. Recent advancements have aimed to overcome this constraint by harnessing image generative models, pretrained on extensive curated web datasets, using knowledge transfer techniques like Score Distillation Sampling (SDS). Efficiently addressing the requirements of high-resolution rendering often necessitates the adoption of latent representation-based models, such as the Latent Diffusion Model (LDM). In this framework, a significant challenge arises: To compute gradients for individual image pixels, it is necessary to backpropagate gradients from the designated latent space through the frozen components of the image model, such as the VAE encoder used within LDM. However, this gradient propagation pathway has never been optimized, remaining uncontrolled during training. We find that the unregulated gradients adversely affect the 3D model's capacity in acquiring texture-related information from the image generative model, leading to poor quality appearance synthesis. To address this overarching challenge, we propose an innovative operation termed Pixel-wise Gradient Clipping (PGC) designed for seamless integration into existing 3D generative models, thereby enhancing their synthesis quality. Specifically, we control the magnitude of stochastic gradients by clipping the pixel-wise gradients efficiently, while preserving crucial texture-related gradient directions. Despite this simplicity and minimal extra cost, extensive experiments demonstrate the efficacy of our PGC in enhancing the performance of existing 3D generative models for high-resolution object rendering.

Details

ICLR Conference 2024 Conference Paper

Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting

Zeyu Yang 0004
Hongye Yang
Zijie Pan
Li Zhang 0040

Reconstructing dynamic 3D scenes from 2D images and generating diverse views over time is challenging due to scene complexity and temporal dynamics. Despite advancements in neural implicit models, limitations persist: (i) Inadequate Scene Structure: Existing methods struggle to reveal the spatial and temporal structure of dynamic scenes from directly learning the complex 6D plenoptic function. (ii) Scaling Deformation Modeling: Explicitly modeling scene element deformation becomes impractical for complex dynamics. To address these issues, we consider the spacetime as an entirety and propose to approximate the underlying spatio-temporal 4D volume of a dynamic scene by optimizing a collection of 4D primitives, with explicit geometry and appearance modeling. Learning to optimize the 4D primitives enables us to synthesize novel views at any desired time with our tailored rendering routine. Our model is conceptually simple, consisting of a 4D Gaussian parameterized by anisotropic ellipses that can rotate arbitrarily in space and time, as well as view-dependent and time-evolved appearance represented by the coefficient of 4D spherindrical harmonics. This approach offers simplicity, flexibility for variable-length video and end-to-end training, and efficient real-time rendering, making it suitable for capturing complex dynamic scene motions. Experiments across various benchmarks, including monocular and multi-view scenarios, demonstrate our 4DGS model's superior visual quality and efficiency.

Details

ICML Conference 2024 Conference Paper

S2IP-LLM: Semantic Space Informed Prompt Learning with LLM for Time Series Forecasting

Zijie Pan
Yushan Jiang
Sahil Garg
Anderson Schneider
Yuriy Nevmyvaka
Dongjin Song

Recently, there has been a growing interest in leveraging pre-trained large language models (LLMs) for various time series applications. However, the semantic space of LLMs, established through the pre-training, is still underexplored and may help yield more distinctive and informative representations to facilitate time series forecasting. To this end, we propose Semantic Space Informed Prompt learning with LLM ($S^2$IP-LLM) to align the pre-trained semantic space with time series embedding space and perform time series forecasting based on learned prompts from the joint space. We first design a tokenization module tailored for cross-modality alignment, which explicitly concatenates patches of decomposed time series components to create embeddings that effectively encode the temporal dynamics. Next, we leverage the pre-trained word token embeddings to derive semantic anchors and align selected anchors with time series embeddings by maximizing the cosine similarity in the joint space. This way, $S^2$IP-LLM can retrieve relevant semantic anchors as prompts to provide strong indicators (context) for time series that exhibit different temporal dynamics. With thorough empirical studies on multiple benchmark datasets, we demonstrate that the proposed $S^2$IP-LLM can achieve superior forecasting performance over state-of-the-art baselines. Furthermore, our ablation studies and visualizations verify the necessity of prompt learning informed by semantic space.

Details

NeurIPS Conference 2024 Conference Paper

Tetrahedron Splatting for 3D Generation

Chun Gu
Zeyu Yang
Zijie Pan
Xiatian Zhu
Li Zhang

3D representation is essential to the significant advance of 3D generation with 2D diffusion priors. As a flexible representation, NeRF has been first adopted for 3D representation. With density-based volumetric rendering, it however suffers both intensive computational overhead and inaccurate mesh extraction. Using a signed distance field and Marching Tetrahedra, DMTet allows for precise mesh extraction and real-time rendering but is limited in handling large topological changes in meshes, leading to optimization challenges. Alternatively, 3D Gaussian Splatting (3DGS) is favored in both training and rendering efficiency while falling short in mesh extraction. In this work, we introduce a novel 3D representation, Tetrahedron Splatting (TeT-Splatting), that supports easy convergence during optimization, precise mesh extraction, and real-time rendering simultaneously. This is achieved by integrating surface-based volumetric rendering within a structured tetrahedral grid while preserving the desired ability of precise mesh extraction, and a tile-based differentiable tetrahedron rasterizer. Furthermore, we incorporate eikonal and normal consistency regularization terms for the signed distance field to improve generation quality and stability. Critically, our representation can be trained without mesh extraction, making the optimization process easier to converge. Our TeT-Splatting can be readily integrated in existing 3D generation pipelines, along with polygonal mesh for texture optimization. Extensive experiments show that our TeT-Splatting strikes a superior tradeoff among convergence speed, render efficiency, and mesh quality as compared to previous alternatives under varying 3D generation settings.

PDF Details DOI