Visualizations play a crucial part in effective communication of concepts and information. Recent advances in reasoning and retrieval augmented generation have enabled Large Language Models (LLMs) to perform deep research and generate comprehensive reports. Despite its progress, existing deep research frameworks primarily focus on generating text-only content, leaving the automated generation of interleaved texts and visualizations underexplored. This novel task poses key challenges in designing informative visualizations and effectively integrating them with text reports. To address these challenges, we propose Formal Description of Visualization (FDV), a structured textual representation of charts that enables LLMs to learn from and generate diverse, high-quality visualizations. Building on this representation, we introduce Multimodal DeepResearcher, an agentic framework that decomposes the task into four stages: (1) researching, (2) exemplar report textualization, (3) planning and (4) multimodal report generation. For the evaluation of the generated reports, we develop MultimodalReportBench which contains 100 diverse topics as inputs, and a set of dedicated metrics for report and chart evaluation. Extensive experiments across models and evaluation methods demonstrate the effectiveness of Multimodal DeepResearcher. Notably, utilizing the same Claude 3.7 Sonnet model, Multimodal DeepResearcher achieves an 82% overall win rate over the baseline method.

Business intelligence (BI) transforms large volumes of data within modern organizations into actionable insights for informed decision-making. Recently, large language model (LLM)-based agents have streamlined the BI workflow by automatically performing task planning, reasoning, and actions in executable environments based on natural language (NL) queries. However, existing approaches primarily focus on individual BI tasks such as NL2SQL and NL2VIS. The fragmentation of tasks across different data roles and tools lead to inefficiencies and potential errors due to the iterative and collaborative nature of BI. In this paper, we introduce DataLab, a unified BI platform that integrates a one-stop LLM-based agent framework with an augmented computational notebook interface. DataLab supports various BI tasks for different data roles in data preparation, analysis, and visualization by seamlessly combining LLM assistance with user customization within a single environment. To achieve this unification, we design a domain knowledge incorporation module tailored for enterprise-specific BI tasks, an inter-agent communication mechanism to facilitate information sharing across the BI workflow, and a cell-based context management strategy to enhance context utilization efficiency in BI notebooks. Extensive experiments demonstrate that DataLab achieves state-of-the-art performance on various BI tasks across popular research benchmarks. Moreover, DataLab maintains high effectiveness and efficiency on real-world datasets from Tencent, achieving up to a 58.58% increase in accuracy and a 61.65 % reduction in token cost on enterprise-specific BI tasks.

The proliferation of large language models (LLMs) has revolutionized the capabilities of natural language interfaces (NLIs) for data analysis. LLMs can perform multi-step and complex reasoning to generate data insights based on users' analytic intents. However, these insights often entangle with an abundance of contexts in analytic conversations such as code, visualizations, and natural language explanations. This hinders efficient recording, organization, and navigation of insights within the current chat-based LLM interfaces. In this paper, we first conduct a formative study with eight data analysts to understand their general workflow and pain points of insight management during LLM-powered data analysis. Accordingly, we introduce InsightLens, an interactive system to overcome such challenges. Built upon an LLM-agent-based framework that automates insight recording and organization along with the analysis process, InsightLens visualizes the complex conversational contexts from multiple aspects to facilitate insight navigation. A user study with twelve data analysts demonstrates the effectiveness of InsightLens, showing that it significantly reduces users' manual and cognitive effort without disrupting their conversational data analysis workflow, leading to a more efficient analysis experience.

Zhaorui Yang, Tianyu Pang, Haozhe Feng, Han Wang, Wei Chen, Minfeng Zhu, Qian Liu. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

This paper presents GraphFederator, a novel approach to construct federated representations of multi-party graphs and supports privacy-preserving visual analysis of graphs. Inspired by the concept of federated learning, we reformulate the analysis of multi-party graphs into a decentralization process. The new federation framework consists of a shared module that is responsible for federated modeling and analysis, and a set of local modules that run on respective graph data. Specifically, we propose a Federated Graph Representation Model (FGRM) that is learned from encrypted characteristics of multi-party graphs in local modules. We also design multiple visualization tools for federated visualization, exploration, and analysis of multi-party graphs. Experimental results on two datasets demonstrate the effectiveness of our approach.

Patterns in charts refer to interesting visual features or forms. Identifying patterns not only helps analysts understand the ‘shape’ of the data but also supports better and faster decision-making. Existing solutions for identifying patterns in charts require a large number of labeled data instances, making it intractable without user supervision. In this paper, we propose ChartNavigator, an interactive pattern identification and annotation framework for unlabeled visualization charts. ChartNavigator leverages a novel chart-sensitive deep factor model to map patterns into a low-dimensional factor representation space, and facilitates rich analysis with the derived representations. We design and implement a visual interface to support efficient identification and annotation of potential patterns in charts. Evaluations with multiple datasets show that our approach outperforms the baseline models in identifying and annotating patterns

Data privacy is an essential issue in publishing data visualizations. However, it is challenging to represent multiple data patterns in privacy-preserving visualizations. The prior approaches target specific chart types or perform an anonymization model uniformly without considering the importance of data patterns in visualizations. In this paper, we propose a visual analytics approach that facilitates data custodians to generate multiple private charts while maintaining user-preferred patterns. To this end, we introduce pattern constraints to model users' preferences over data patterns in the dataset and incorporate them into the proposed Bayesian network-based Differential Privacy (DP) model PriVis. A prototype system, DPVisCreator, is developed to assist data custodians in implementing our approach. The effectiveness of our approach is demonstrated with quantitative evaluation of pattern utility under the different levels of privacy protection, case studies, and semi-structured expert interviews.

Modeling multivariate time series (MTS) is critical in modern intelligent systems. The accurate forecast of MTS data is still challenging due to the complicated latent variable correlation. Recent works apply the Graph Neural Networks (GNNs) to the task, with the basic idea of representing the correlation as a static graph. However, predicting with a static graph causes significant bias because the correlation is time-varying in the real-world MTS data. Besides, there is no gap analysis between the actual correlation and the learned one in their works to validate the effectiveness. This paper proposes a temporal polynomial graph neural network (TPGNN) for accurate MTS forecasting, which represents the dynamic variable correlation as a temporal matrix polynomial in two steps. First, we capture the overall correlation with a static matrix basis. Then, we use a set of time-varying coefficients and the matrix basis to construct a matrix polynomial for each time step. The constructed result empirically captures the precise dynamic correlation of six synthetic MTS datasets generated by a non-repeating random walk model. Moreover, the theoretical analysis shows that TPGNN can achieve perfect approximation under a commutative condition. We conduct extensive experiments on two traffic datasets with prior structure and four benchmark datasets. The results indicate that TPGNN achieves the state-of-the-art on both short-term and long-term MTS forecastings.

Semi-supervised variational autoencoders (VAEs) have obtained strong results, but have also encountered the challenge that good ELBO values do not always imply accurate inference results.In this paper, we investigate and propose two causes of this problem: (1) The ELBO objective cannot utilize the label information directly. (2) A bottleneck value exists, and continuing to optimize ELBO after this value will not improve inference accuracy. On the basis of the experiment results, we propose SHOT-VAE to address these problems without introducing additional prior knowledge. The SHOT-VAE offers two contributions: (1) A new ELBO approximation named smooth-ELBO that integrates the label predictive loss into ELBO. (2) An approximation based on optimal interpolation that breaks the ELBO value bottleneck by reducing the margin between ELBO and the data likelihood. The SHOT-VAE achieves good performance with 25.30% error rate on CIFAR-100 with 10k labels and reduces the error rate to 6.11% on CIFAR-10 with 4k labels.

Conventional unsupervised multi-source domain adaptation (UMDA) methods assume all source domains can be accessed directly. However, this assumption neglects the privacy-preserving policy, where all the data and computations must be kept decentralized. There exist three challenges in this scenario: (1) Minimizing the domain distance requires the pairwise calculation of the data from the source and target domains, while the data on the source domain is not available. (2) The communication cost and privacy security limit the application of existing UMDA methods, such as the domain adversarial training. (3) Since users cannot govern the data quality, the irrelevant or malicious source domains are more likely to appear, which causes negative transfer. To address the above problems, we propose a privacy-preserving UMDA paradigm named Knowledge Distillation based Decentralized Domain Adaptation (KD3A), which performs domain adaptation through the knowledge distillation on models from different source domains. The extensive experiments show that KD3A significantly outperforms state-of-the-art UMDA approaches. Moreover, the KD3A is robust to the negative transfer and brings a 100x reduction of communication cost compared with other decentralized UMDA methods.