arXiv subjects

Zhihao Ding

Publications and source records attributed to Zhihao Ding.

13 recordsLinked to original sources

arXiv2026

QwenPaw-Data: Bridging Facts, Methodology, and Execution for Autonomous Enterprise Data Analytics

Enterprise data analysis is emerging as a distinct frontier for autonomous agents. Compared with general-purpose interaction and software engineering, it operates in an open, ambiguous, and continuously evolving environment. These characteristics call for a data-agent architecture that treats semantics, methodology, execution, and evolution as first-class system concerns. To this end, we introduce QwenPaw-Data, an agentic data system designed for enterprise intelligent data analysis. QwenPaw-Data consolidates heterogeneous assets from warehouses, dashboards, documents, interaction logs, and historical tasks into reusable, governable, and evolvable analysis assets, then turns natural-language requests into end-to-end analytical workflows spanning data understanding, retrieval, analysis, report generation, and decision support. Its architecture decomposes the problem into three collaborative subsystems: DataBridge provides trustworthy semantic grounding through interconnected metadata, knowledge, and trace graphs; Skill-Hub codifies expert analytical methodology into reusable and verifiable skills; and Host materializes these evidence and method assets into controllable, artifact-centric runtime execution. Across these subsystems, semantics, methods, traces, and feedback are continuously deposited back into the system, forming a self-evolving asset flywheel. Experiments on public benchmarks and real-world industrial BI workloads show that QwenPaw-Data improves both verifiable data access capability and higher-level analytical quality, offering a practical foundation for reliable, traceable, and continuously improving enterprise data agents.

cs.AI↗

arXiv2026

Efficient and Effective Table-Centric Table Union Search in Data Lakes

In data lakes, information on the same subject is often fragmented across multiple tables. Table union search aims to find the top-k tables that can be unioned with a query table to extend it with more rows, without relying on metadata or ground-truth labels. Existing methods are mainly column-centric: they focus on modeling column unionability scores using column embeddings, which are then used throughout the search process for column matching, filtering, and aggregation. However, this overlooks holistic table-level semantics, which may result in suboptimal rankings and inefficiencies. We introduce TACTUS, a novel table-centric method for table union search. Unlike prior work that searches from columns to tables, we search in a table-first way and examine columns only in the final step. During offline processing, we directly generate table embeddings for holistic, table-level unionability scoring by designing table-level representation techniques, including positive table pair construction to simulate unionable tables, two-pronged negative table sampling to avoid latent positives and mine hard negatives to enhance representation quality, and attentive table encoding for effective embeddings. During online search, we first develop a table-centric adaptive candidate retrieval method that efficiently selects a compact, high-quality candidate pool by leveraging the distribution of table-level unionability scores induced by table embeddings. We then inspect columns only within this compact candidate set and design a dual-evidence reranking technique that integrates table-level and column-level scores to refine the final top-k results. Extensive experiments on real-world datasets show that TACTUS significantly improves result quality while being much faster than existing methods in both offline and online processing, often by an order of magnitude.

cs.DB↗

arXiv2026

FlexGuard: Continuous Risk Scoring for Strictness-Adaptive LLM Content Moderation

Ensuring the safety of LLM-generated content is essential for real-world deployment. Most existing guardrail models formulate moderation as a fixed binary classification task, implicitly assuming a fixed definition of harmfulness. In practice, enforcement strictness - how conservatively harmfulness is defined and enforced - varies across platforms and evolves over time, making binary moderators brittle under shifting requirements. We first introduce FlexBench, a strictness-adaptive LLM moderation benchmark that enables controlled evaluation under multiple strictness regimes. Experiments on FlexBench reveal substantial cross-strictness inconsistency in existing moderators: models that perform well under one regime can degrade substantially under others, limiting their practical usability. To address this, we propose FlexGuard, an LLM-based moderator that outputs a calibrated continuous risk score reflecting risk severity and supports strictness-specific decisions via thresholding. We train FlexGuard via risk-alignment optimization to improve score-severity consistency and provide practical threshold selection strategies to adapt to target strictness at deployment. Experiments on FlexBench and public benchmarks demonstrate that FlexGuard achieves higher moderation accuracy and substantially improved robustness under varying strictness. We release the source code and data to support reproducibility.

cs.LG↗

arXiv2025

Retrieve-and-Verify: A Table Context Selection Framework for Accurate Column Annotations

Tables are a prevalent format for structured data, yet their metadata, such as semantic types and column relationships, is often incomplete or ambiguous. Column annotation tasks, including Column Type Annotation (CTA) and Column Property Annotation (CPA), address this by leveraging table context, which are critical for data management. Existing methods typically serialize all columns in a table into pretrained language models to incorporate context, but this coarse-grained approach often degrades performance in wide tables with many irrelevant or misleading columns. To address this, we propose a novel retrieve-and-verify context selection framework for accurate column annotation, introducing two methods: REVEAL and REVEAL+. In REVEAL, we design an efficient unsupervised retrieval technique to select compact, informative column contexts by balancing semantic relevance and diversity, and develop context-aware encoding techniques with role embeddings and target-context pair training to effectively differentiate target and context columns. To further improve performance, in REVEAL+, we design a verification model that refines the selected context by directly estimating its quality for specific annotation tasks. To achieve this, we formulate a novel column context verification problem as a classification task and then develop the verification model. Moreover, in REVEAL+, we develop a top-down verification inference technique to ensure efficiency by reducing the search space for high-quality context subsets from exponential to quadratic. Extensive experiments on six benchmark datasets demonstrate that our methods consistently outperform state-of-the-art baselines.

cs.DB↗

arXiv2025

E2Former: An Efficient and Equivariant Transformer with Linear-Scaling Tensor Products

Equivariant Graph Neural Networks (EGNNs) have demonstrated significant success in modeling microscale systems, including those in chemistry, biology and materials science. However, EGNNs face substantial computational challenges due to the high cost of constructing edge features via spherical tensor products, making them impractical for large-scale systems. To address this limitation, we introduce E2Former, an equivariant and efficient transformer architecture that incorporates the Wigner $6j$ convolution (Wigner $6j$ Conv). By shifting the computational burden from edges to nodes, the Wigner $6j$ Conv reduces the complexity from $O(|\mathcal{E}|)$ to $ O(| \mathcal{V}|)$ while preserving both the model's expressive power and rotational equivariance. We show that this approach achieves a 7x-30x speedup compared to conventional $\mathrm{SO}(3)$ convolutions. Furthermore, our empirical results demonstrate that the derived E2Former mitigates the computational challenges of existing approaches without compromising the ability to capture detailed geometric information. This development could suggest a promising direction for scalable and efficient molecular modeling.

cs.LG↗

arXiv2024

TINED: GNNs-to-MLPs by Teacher Injection and Dirichlet Energy Distillation

Graph Neural Networks (GNNs) are pivotal in graph-based learning, particularly excelling in node classification. However, their scalability is hindered by the need for multi-hop data during inference, limiting their application in latency-sensitive scenarios. Recent efforts to distill GNNs into multi-layer perceptrons (MLPs) for faster inference often underutilize the layer-level insights of GNNs. In this paper, we present TINED, a novel approach that distills GNNs to MLPs on a layer-by-layer basis using Teacher Injection and Dirichlet Energy Distillation techniques. We focus on two key operations in GNN layers: feature transformation (FT) and graph propagation (GP). We recognize that FT is computationally equivalent to a fully-connected (FC) layer in MLPs. Thus, we propose directly transferring teacher parameters from an FT in a GNN to an FC layer in the student MLP, enhanced by fine-tuning. In TINED, the FC layers in an MLP replicate the sequence of FTs and GPs in the GNN. We also establish a theoretical bound for GP approximation. Furthermore, we note that FT and GP operations in GNN layers often exhibit opposing smoothing effects: GP is aggressive, while FT is conservative. Using Dirichlet energy, we develop a DE ratio to measure these effects and propose Dirichlet Energy Distillation to convey these characteristics from GNN layers to MLP layers. Extensive experiments show that TINED outperforms GNNs and leading distillation methods across various settings and seven datasets. Source code are available at https://github.com/scottjiao/TINED_ICML25/.

cs.LG↗

arXiv2024

RingFormer: A Ring-Enhanced Graph Transformer for Organic Solar Cell Property Prediction

Organic Solar Cells (OSCs) are a promising technology for sustainable energy production. However, the identification of molecules with desired OSC properties typically involves laborious experimental research. To accelerate progress in the field, it is crucial to develop machine learning models capable of accurately predicting the properties of OSC molecules. While graph representation learning has demonstrated success in molecular property prediction, it remains underexplored for OSC-specific tasks. Existing methods fail to capture the unique structural features of OSC molecules, particularly the intricate ring systems that critically influence OSC properties, leading to suboptimal performance. To fill the gap, we present RingFormer, a novel graph transformer framework specially designed to capture both atom and ring level structural patterns in OSC molecules. RingFormer constructs a hierarchical graph that integrates atomic and ring structures and employs a combination of local message passing and global attention mechanisms to generate expressive graph representations for accurate OSC property prediction. We evaluate RingFormer's effectiveness on five curated OSC molecule datasets through extensive experiments. The results demonstrate that RingFormer consistently outperforms existing methods, achieving a 22.77% relative improvement over the nearest competitor on the CEPDB dataset.

cs.LG↗

arXiv2024

Fabrication of Spin-1/2 Heisenberg Antiferromagnetic Chains via Combined On-surface Synthesis and Reduction for Spinon Detection

Spin-1/2 Heisenberg antiferromagnetic chains are excellent one-dimensional platforms for exploring quantum magnetic states and quasiparticle fractionalization. Understanding its quantum magnetism and quasiparticle excitation at the atomic scale is crucial for manipulating the quantum spin systems. Here, we report the fabrication of spin-1/2 Heisenberg chains through on-surface synthesis and in-situ reduction. A closed-shell nanographene is employed as a precursor for Ullman coupling to avoid radical fusing, thus obtaining oligomer chains. Following exposure to atomic hydrogen and tip manipulation, closed-shell polymers are transformed into spin-1/2 chains with controlled lengths by reducing the ketone groups and subsequent hydrogen desorption. The spin excitation gaps are found to decrease in power-law as the chain lengths, suggesting its gapless feature. More interestingly, the spinon dispersion is extracted from the inelastic spectroscopic spectra, agreeing well with the calculations. Our results demonstrate the great potential of fabricating desired quantum systems through a combined on-surface synthesis and reduction approach.

cond-mat.mes-hall↗

arXiv2024

Effective Illicit Account Detection on Large Cryptocurrency MultiGraphs

Cryptocurrencies are rapidly expanding and becoming vital in digital financial markets. However, the rise in cryptocurrency-related illicit activities has led to significant losses for users. To protect the security of these platforms, it is critical to identify illicit accounts effectively. Current detection methods mainly depend on feature engineering or are inadequate to leverage the complex information within cryptocurrency transaction networks, resulting in suboptimal performance. In this paper, we present DIAM, an effective method for detecting illicit accounts in cryptocurrency transaction networks modeled by directed multi-graphs with attributed edges. DIAM first features an Edge2Seq module that captures intrinsic transaction patterns from parallel edges by considering edge attributes and their directed sequences, to generate effective node representations. Then in DIAM, we design a multigraph Discrepancy (MGD) module with a tailored message passing mechanism to capture the discrepant features between normal and illicit nodes over the multigraph topology, assisted by an attention mechanism. DIAM integrates these techniques for end-to-end training to detect illicit accounts from legitimate ones. Extensive experiments, comparing against 15 existing solutions on 4 large cryptocurrency datasets of Bitcoin and Ethereum, demonstrate that DIAM consistently outperforms others in accurately identifying illicit accounts. For example, on a Bitcoin dataset with 20 million nodes and 203 million edges, DIAM attains an F1 score of 96.55%, markedly surpassing the runner-up's score of 83.92%. The code is available at https://github.com/TommyDzh/DIAM.

cs.LG↗

arXiv2024

SGOOD: Substructure-enhanced Graph-Level Out-of-Distribution Detection

Graph-level representation learning is important in a wide range of applications. Existing graph-level models are generally built on i.i.d. assumption for both training and testing graphs. However, in an open world, models can encounter out-of-distribution (OOD) testing graphs that are from different distributions unknown during training. A trustworthy model should be able to detect OOD graphs to avoid unreliable predictions, while producing accurate in-distribution (ID) predictions. To achieve this, we present SGOOD, a novel graph-level OOD detection framework. We find that substructure differences commonly exist between ID and OOD graphs, and design SGOOD with a series of techniques to encode task-agnostic substructures for effective OOD detection. Specifically, we build a super graph of substructures for every graph, and develop a two-level graph encoding pipeline that works on both original graphs and super graphs to obtain substructure-enhanced graph representations. We then devise substructure-preserving graph augmentation techniques to further capture more substructure semantics of ID graphs. Extensive experiments against 11 competitors on numerous graph datasets demonstrate the superiority of SGOOD, often surpassing existing methods by a significant margin. The code is available at https://github.com/TommyDzh/SGOOD.

cs.LG↗

arXiv2024

Large Language Models are In-Context Molecule Learners

Large Language Models (LLMs) have demonstrated exceptional performance in biochemical tasks, especially the molecule caption translation task, which aims to bridge the gap between molecules and natural language texts. However, previous methods in adapting LLMs to the molecule-caption translation task required extra domain-specific pre-training stages, suffered weak alignment between molecular and textual spaces, or imposed stringent demands on the scale of LLMs. To resolve the challenges, we propose In-Context Molecule Adaptation (ICMA), as a new paradigm allowing LLMs to learn the molecule-text alignment from context examples via In-Context Molecule Tuning. Specifically, ICMA incorporates the following three stages: Hybrid Context Retrieval, Post-retrieval Re-ranking, and In-context Molecule Tuning. Initially, Hybrid Context Retrieval utilizes BM25 Caption Retrieval and Molecule Graph Retrieval to retrieve similar informative context examples. Additionally, Post-retrieval Re-ranking is composed of Sequence Reversal and Random Walk selection to further improve the quality of retrieval results. Finally, In-Context Molecule Tuning unlocks the in-context learning and reasoning capability of LLMs with the retrieved examples and adapts the parameters of LLMs for better alignment between molecules and texts. Experimental results demonstrate that ICMA can empower LLMs to achieve state-of-the-art or comparable performance without extra training corpora and intricate structures, showing that LLMs are inherently in-context molecule learners.

cs.CL↗

arXiv2021

Infer-AVAE: An Attribute Inference Model Based on Adversarial Variational Autoencoder

User attributes, such as gender and education, face severe incompleteness in social networks. In order to make this kind of valuable data usable for downstream tasks like user profiling and personalized recommendation, attribute inference aims to infer users' missing attribute labels based on observed data. Recently, variational autoencoder (VAE), an end-to-end deep generative model, has shown promising performance by handling the problem in a semi-supervised way. However, VAEs can easily suffer from over-fitting and over-smoothing when applied to attribute inference. To be specific, VAE implemented with multi-layer perceptron (MLP) can only reconstruct input data but fail in inferring missing parts. While using the trending graph neural networks (GNNs) as encoder has the problem that GNNs aggregate redundant information from neighborhood and generate indistinguishable user representations, which is known as over-smoothing. In this paper, we propose an attribute \textbf{Infer}ence model based on \textbf{A}dversarial \textbf{VAE} (Infer-AVAE) to cope with these issues. Specifically, to overcome over-smoothing, Infer-AVAE unifies MLP and GNNs in encoder to learn positive and negative latent representations respectively. Meanwhile, an adversarial network is trained to distinguish the two representations and GNNs are trained to aggregate less noise for more robust representations through adversarial training. Finally, to relieve over-fitting, mutual information constraint is introduced as a regularizer for decoder, so that it can make better use of auxiliary information in representations and generate outputs not limited by observations. We evaluate our model on 4 real-world social network datasets, experimental results demonstrate that our model averagely outperforms baselines by 7.0$\%$ in accuracy.

cs.LG↗

arXiv2018

Mobility Based Routing Protocol with MAC Collision Improvement in Vehicular Ad Hoc Networks

Intelligent transportation system attracts a great deal of research attention because it helps enhance traffic safety, improve driving experiences, and transportation efficiency. Vehicular Ad Hoc Network (VANET) supports wireless connections among vehicles and offers information exchange, thus significantly facilitating intelligent transportation systems. Since the vehicles move fast and often change lanes unpredictably, the network topology evolves rapidly in a random fashion, which imposes diverse challenges in routing protocol design over VANET. When it comes to the 5G era, the fulfilment of ultra low end-to-end delay and ultra high reliability becomes more crucial than ever. In this paper, we propose a novel routing protocol that incorporates mobility status and MAC layer channel contention information. The proposed routing protocol determines next hop by applying mobility information and MAC contention information which differs from existing greedy perimeter stateless routing (GPSR) protocol. Simulation results of the proposed routing protocol show its performance superiority over the existing approach.

cs.OH↗