arXiv subjects

Shixun Huang

Publications and source records attributed to Shixun Huang.

17 recordsLinked to original sources

arXiv2026

CausalNav: Reliability-Certified Causal World Models for Control under Physical-Parameter Shift

A world model is only useful for physical AI if it changes what the agent does, and only safe if it declines to do so when it is wrong. We study both halves of that requirement with CausalNav, a controller built around a signed, action-conditioned transition graph over identified state coordinates. At deployment CausalNav simulates a small library of intervention sequences, converts their objective error into policy-logit advice, and admits that advice only when a scale-free predictive-reliability certificate, a policy-margin gate, and an argmax-agreement gate all pass; otherwise it falls back exactly to its own model-based base controller. We evaluate against nine controlled baselines (transformer, recurrent, split-latent, graph, causal-induction, and three recent model-based reasoning modules) on CartPole-v1 and discretized Pendulum-v1 with physical-parameter shifts, under one shared PPO trainer, one interaction budget, and ten held-out seeds (200 runs). CausalNav attains the best average rank (1.25 of ten). The diagnostic result is more informative than the ranking: the learned graph recovers structure well above chance (CartPole F1 = 0.59 +/- 0.09), yet per-seed structural fidelity is uncorrelated with per-seed control benefit (r = -0.15, p = 0.67), and the certificate abstains on 10/10 Pendulum seeds, where forcing the planner on costs return. Model fidelity did not predict downstream control utility in our setting; certified abstention, not better prediction, is what made the world model safe to deploy.

cs.AI↗

arXiv2026

When the Judge Should Not Decide: Evidence-Locked, Non-Compensatory Selection Bounds LLM-Judge Failure in Reasoning Pipelines

An LLM judge deployed inside a reasoning pipeline does not merely measure quality, it decides which answer ships. We show that the cost of that decision depends less on judge accuracy than on the decision rule the judge is embedded in. On frozen candidate pools from four GRPO policies, an unconstrained scalar DeepSeek-R1-7B judge buys almost nothing over answer-level majority vote (+1.0 pp on 500 GSM8K questions, +0.34 EM on 300 HotpotQA questions), and on a frozen-rule 30-question confirmation split it is 10 points worse than majority, a judge that destroys accuracy while scoring candidates confidently. We then subordinate the same judge to Evidence-Locked Derive-Gate-Repair (EL-DGR), a task-adaptive non-compensatory rule under which a judge preference may override evidence-supported consensus only with an extractive evidence certificate, and a repair only when neither alternative is certified and the repair is. With no change to the judge, the candidates, or the budget, EL-DGR reaches 58.2% on GSM8K (vs. 56.8% judge, 55.8% majority, 55.4% first candidate) and 17.33 EM / 25.46 F1 on HotpotQA (vs. 15.67/23.49, 15.33/23.19, 15.33/22.97), improving on first-candidate GRPO by +2.8 pp (exact McNemar p=0.0026) and +2.00 EM (p=0.070, borderline). A decision audit shows why: EL-DGR overturns consensus on only 8 of 30 pilot questions and never converts a correct consensus into an incorrect answer. We also report what did not work: the same seven-channel decomposition used as a step-level gated training reward is null, and corrected channel-drop ablations show no channel is individually necessary (p=1.0 throughout). The practitioner-facing finding is negative about judges and positive about admissibility, bound the judge's blast radius rather than trying to make it accurate.

cs.AI↗

arXiv2026

Alignment-Guided Largest Table Overlap Size Estimation

Fast estimation of the size of the largest overlap between tables enables blocking and query-by-table retrieval in large table repositories. The first and the state-of-the-art estimator Armadillo improves efficiency by embedding each table independently and approximating overlap ratio via embedding similarity. However, accurate estimation in heterogeneous repositories remains limited by three challenges: (C1) overlap depends on row-column structure, i.e., each matched cell must preserve both its row and column membership under a joint alignment of the two tables, but existing encodings leave this structure to be inferred indirectly; (C2) independent encoding provides no explicit channel for inter-table alignment signals, biasing prediction toward global similarity; (C3) naive value encodings overfit to corpus-specific distributions, causing cross-domain degradation. Hence, we propose ALORE, a scalable and domain-robust overlap ratio estimator built on three principles: (P1) explicitly represent row-column structure; (P2) expose inter-table alignment signals during training without expensive alignment search; (P3) reduce sensitivity to corpus-specific value distributions. ALORE instantiates these principles with a Two-View Row-Column Hypergraph encoder, alignment-guided objectives with inexpensive interaction signals, and a domain-robust value mapping. Experiments on multiple datasets spanning diverse domains and scales, including a large real-world corpus beyond prior benchmarks, show that ALORE outperforms the state of the art. ALORE reduces MAE by up to 55% overall and 69% in zero-shot transfer, while achieving up to 89x speedup. We further validate its effectiveness for query-by-table retrieval.

cs.CL↗

arXiv2026

LEARNT: A Practical Estimator for Cardinality of LIKE Queries with Formal Accuracy Guarantees

We study the problem of cardinality estimation for LIKE queries on string data, focusing on the most common patterns in real workloads: prefix, suffix, and substring queries. We propose LEARNT, a LIKE query Estimator with Accuracy, Robustness, Negligible overhead, Tunability, and Theoretical guarantees. LEARNT formulates estimation as a bucket-classification problem, and upon correct classification, it yields formal bounds on Q-error for the queries with non-empty answer. It employs a memory-efficient bucketed layered-filter architecture with Bloom filters and compact auxiliary tables, together with optimizations that exploit query skew to reduce storage. For the queries that have empty answer, LEARNT incorporates dedicated filter-based and prefix-walk strategies, providing probabilistic guarantees on correct identification. Furthermore, to support arbitrarily long query strings, we extend LEARNT with Markov modeling scheme that composes short-query statistics into estimates for longer queries. A theoretical framework guides parameter selection to minimize storage under accuracy and robustness constraints. Extensive experiments on four real-world datasets show that LEARNT consistently outperforms state-of-the-art methods such as CLIQUE and LPLM, achieving 1.3-1.7x lower mean Q-error, significantly lower tail errors, and up to 70x faster construction with comparable memory usage.

cs.DB↗

arXiv2026

Closing Trajectories: Equation-Free Cyclic Animation via Koopman Surrogates

Cyclic animation is widely used in computer graphics and interactive content.It supports seamless playback in games, VR, and interactive simulation,where short clips must repeat smoothly over long durations. Achievingphysically plausible cyclic synthesis from an input sequence is challengingbecause the endpoint states of the observed sequence rarely match exactly,and the governing equations of the underlying system are often unavailable.We therefore propose an equation-free framework that identiffes a Koopmansurrogate from the observed trajectory and computes a cyclic trajectory byapplying a Fourier-parameterized, time-varying control force under a hardtemporal periodicity constraint. The resulting formulation reduces cyclicsynthesis to a linearly constrained quadratic program that can be solvedefffciently through a structured KKT system. Our method is applicable toa diverse range of examples, including N-body systems, cloth, deformableobjects, shallow water, etc.

cs.GR↗

arXiv2026

Unified Data Discovery across Query Modalities and User Intents

Data discovery - retrieving relevant tables from a data lake in response to user queries - is a fundamental building block for downstream analytics. In practice, data discovery must support different query modalities, including natural language (NL) statements and tables, and accommodate diverse user intents, ranging from open-ended enrichment to task-driven inference for applications such as table question answering and fact verification. However, most existing methods are designed for a single query modality or a specific user intent, limiting their generalizability. We propose UniDisc, a unified data discovery framework that supports both NL statements and tables as queries and generalizes across diverse user intents without intent-specific representations or relevance modeling. UniDisc learns a common cross-modal representation model that produces unified representations for queries of different modalities and candidate tables, enabling uniform relevance assessment across discovery scenarios. Since learning such a model typically requires large labeled collections of query-table pairs, which are expensive to obtain, UniDisc instead exploits contextual signals naturally available in data lakes. Specifically, it models NL statements and tables as nodes in a heterogeneous graph with multiple edge types, and applies dual-view neighbor aggregation and joint optimization to learn robust, context-aware representations under limited supervision. These representations support flexible relevance estimation during retrieval. Experiments on seven datasets show that UniDisc consistently outperforms strong baselines on both NL- and table-based discovery.

cs.DB↗

arXiv2026

A Cross-graph Tuning-free GNN Prompting Framework

GNN prompting aims to adapt models across tasks and graphs without requiring extensive retraining. However, most existing graph prompt methods still require task-specific parameter updates and face the issue of generalizing across graphs, limiting their performance and undermining the core promise of prompting. In this work, we introduce a Cross-graph Tuning-free Prompting Framework (CTP), which supports both homogeneous and heterogeneous graphs, can be directly deployed to unseen graphs without further parameter tuning, and thus enables a plug-and-play GNN inference engine. Extensive experiments on few-shot prediction tasks show that, compared to SOTAs, CTP achieves an average accuracy gain of 30.8% and a maximum gain of 54%, confirming its effectiveness and offering a new perspective on graph prompt learning.

cs.LG↗

arXiv2026

Graph-centric Cross-model Data Integration and Analytics in a Unified Multi-model Database

Graph-centric cross-model data integration and analytics (GCDIA) refer to tasks that leverage the graph model as a central paradigm to integrate relevant information across heterogeneous data models, such as relational and document, and subsequently perform complex analytics such as regression and similarity computation. As modern applications generate increasingly diverse data and move beyond simple retrieval toward advanced analytical objectives (e.g., prediction and recommendation), GCDIA has become increasingly important. Existing multi-model databases (MMDBs) struggle to efficiently support both integration (GCDI) and analytics (GCDA) in GCDIA. They typically separate graph processing from other models without global optimization for GCDI, while relying on tuple-at-a-time execution for GCDA, leading to limited performance and scalability. To address these limitations, we propose GredoDB, a unified MMDB that natively supports storing graph, relational, and document models, while efficiently processing GCDIA. Specifically, we design 1) topology- and attribute-aware graph operators for efficient predicate-aware traversal, 2) a unified GCDI optimization framework to exploit cross-model correlations, and 3) a parallel GCDA architecture that materializes intermediate results for operator-level execution. Experiments on the widely adopted multi-model benchmark M2Bench demonstrate that, in terms of response time, GredoDB achieves up to 107.89 times and an average of 10.89 times speedup on GCDI, and up to 356.72 times and an average of 37.79 times on GCDA, compared to state-of-the-art (SOTA) MMDBs.

cs.DB↗

arXiv2026

Shape-Agnostic Table Overlap Discovery: A Maximum Common Subhypergraph Approach

Understanding how two tables overlap is useful for many data management tasks, but challenging because tables often differ in row and column orders and lack reliable metadata in practice. Prior work defines the largest rectangular overlap, which identifies the maximal contiguous region of matching cells under row and column permutations. However, real overlaps are rarely rectangular, where many valid matches may lie outside any single contiguous block. In this paper, we introduce the Shape-Agnostic Largest Table Overlap (SALTO), a novel generalized notion of overlap that captures arbitrary-shaped, non-contiguous overlaps between tables. To tackle the combinatorial complexity of row and column permutations, we propose to model each table as a hypergraph, casting SALTO computation into a maximum common subhypergraph problem. We prove their equivalence and show the problem is NP-hard to approximate. To solve it, we propose HyperSplit, a novel branch-and-bound algorithm tailored to table-induced hypergraphs. HyperSplit introduces (i) hypergraph-aware label classes that jointly encode cell values and their row-column memberships to ensure structurally valid correspondences without explicit permutation enumeration, (ii) incidence-guided refinement and upper-bound pruning that leverage row-column connectivity to eliminate infeasible partial matches early, and (iii) a tolerance-based optimization mechanism with a tunable parameter that relaxes pruning by a bounded margin to accelerate convergence, enabling scalable yet accurate overlap discovery. Experiments on real-world datasets show that HyperSplit discovers overlaps more effectively (larger overlaps in up to 78.8% of the cases) and more efficiently than state of the art. Three case studies further demonstrate its practical impact across three tasks: cross-source copy detection, data deduplication, and version comparison.

cs.DB↗

arXiv2026

Updatable Balanced Index for Stable Streaming Similarity Search over Large-Scale Fresh Vectors

As artificial intelligence gains more and more popularity, vectors are one of the most widely used data structures for services such as information retrieval and recommendation. Approximate Nearest Neighbor Search (ANNS), which generally relies on indices optimized for fast search to organize large datasets, has played a core role in these popular services. As the frequency of data shift grows, it is crucial for indices to accommodate new data and support real-time updates. Existing researches adopting two different approaches hold the following drawbacks: 1) approaches using additional buffers to temporarily store new data are resource-intensive and inefficient due to the global rebuilding processes; 2) approaches upgrading the internal index structure suffer from performance degradation because of update congestion and imbalanced distribution in streaming workloads. In this paper, we propose UBIS, an Updatable Balanced Index for stable streaming similarity Search, to resolve conflicts by scheduling concurrent updates and maintain good index quality by reducing imbalanced update cases, when the update frequency grows. Experimental results in the real-world datasets demonstrate that UBIS achieves up to 77% higher search accuracy and 45% higher update throughput on average compared to the state-of-the-art indices in streaming workloads.

cs.DB↗

arXiv2026

Odd-DC: Generalizable Neural Model Reduction via Odd Difference-of-Convex Structure

Model reduction is essential for real-time simulation of deformable objects. Linear techniques such as PCA provide structured and predictable behavior, but their limited expressiveness restricts accuracy under large or nonlinear deformations. Nonlinear model reduction with neural networks offers richer representations and higher compression; however, without structural constraints, the learned mapping from latent coordinates to displacements often generalizes poorly beyond the training distribution. We present an odd difference-of-convex (DC) neural formulation that bridges linear and nonlinear model reduction. Our goal is to obtain a latent space that behaves reliably under unseen load magnitudes and directions. To improve extrapolation in magnitude, we introduce convexity into the decoder to discourage oscillatory responses. Yet convexity alone cannot represent the odd symmetry required by many symmetric systems, which is crucial for generalization to inverse force directions. We therefore adopt a DC formulation that preserves the stabilizing effect of convexity while explicitly enforcing odd symmetry. Practically, we realize this structure using an input-convex neural network (ICNN) augmented with symmetry constraints. Across challenging deformation scenarios with varying magnitudes and reversed load directions, our method demonstrates stronger generalization than unconstrained nonlinear reductions while maintaining compact latent spaces and real-time performance. Our DC formulation extends to both mesh-based and neural-field reductions, demonstrating applicability across multiple classes of neural nonlinear model reduction.

cs.GR↗

arXiv2025

A Hybrid Deep Learning based Carbon Price Forecasting Framework with Structural Breakpoints Detection and Signal Denoising

Accurately forecasting carbon prices is essential for informed energy market decision-making, guiding sustainable energy planning, and supporting effective decarbonization strategies. However, it remains challenging due to structural breaks and high-frequency noise caused by frequent policy interventions and market shocks. Existing studies, including the most recent baseline approaches, have attempted to incorporate breakpoints but often treat denoising and modeling as separate processes and lack systematic evaluation across advanced deep learning architectures, limiting the robustness and the generalization capability. To address these gaps, this paper proposes a comprehensive hybrid framework that integrates structural break detection (Bai-Perron, ICSS, and PELT algorithms), wavelet signal denoising, and three state-of-the-art deep learning models (LSTM, GRU, and TCN). Using European Union Allowance (EUA) spot prices from 2007 to 2024 and exogenous features such as energy prices and policy indicators, the framework constructs univariate and multivariate datasets for comparative evaluation. Experimental results demonstrate that our proposed PELT-WT-TCN achieves the highest prediction accuracy, reducing forecasting errors by 22.35% in RMSE and 18.63% in MAE compared to the state-of-the-art baseline model (Breakpoints with Wavelet and LSTM), and by 70.55% in RMSE and 74.42% in MAE compared to the original LSTM without decomposition from the same baseline study. These findings underscore the value of integrating structural awareness and multiscale decomposition into deep learning architectures to enhance accuracy and interpretability in carbon price forecasting and other nonstationary financial time series.

cs.LG↗

arXiv2025

A Unified Approach for Multi-Granularity Search over Spatial Datasets

There has been increased interest in data search as a means to find relevant datasets or data points in data lakes and repositories. Although approaches have been proposed to support spatial dataset search and data point search, they consider the two types of searches independently. To enable search operations ranging from the coarse-grained dataset level to the fine-grained data point level, we provide an integrated one that supports diverse query types and distance metrics. In this paper, we focus on designing a multi-granularity spatial data search system, called Spadas, that supports both dataset and data point search operations. To address the challenges of the high cost of indexing and susceptibility to outliers, we propose a unified index that can drastically improve query efficiency in various scenarios by organizing data reasonably and removing outliers in datasets. Moreover, to accelerate all data search operations, we propose a set of pruning mechanisms based on the unified index, including fast bound estimation, approximation technique with error bound, and pruning in batch techniques, to effectively filter out non-relevant datasets and points. Finally, we report the results of a detailed experimental evaluation using six spatial data repositories, achieving orders of magnitude faster than the state-of-the-art algorithms and demonstrating the effectiveness by case study. An online spatial data search system of Spadas is also implemented and made accessible to users.

cs.DB↗

arXiv2025

Budgeted Spatial Data Acquisition: When Coverage and Connectivity Matter

Data is undoubtedly becoming a commodity like oil, land, and labor in the 21st century. Although there have been many successful marketplaces for data trading, the existing data marketplaces lack consideration of the case where buyers want to acquire a collection of datasets (instead of one), and the overall spatial coverage and connectivity matter. In this paper, we take the first attempt to formulate this problem as Budgeted Maximum Coverage with Connectivity Constraint (BMCC), which aims to acquire a dataset collection with the maximum spatial coverage under a limited budget while maintaining spatial connectivity. To solve the problem, we propose two approximate algorithms with detailed theoretical guarantees and time complexity analysis, followed by two acceleration strategies to further improve the efficiency of the algorithm. Experiments are conducted on five real-world spatial dataset collections to verify the efficiency and effectiveness of our algorithms.

cs.DB↗

arXiv2025

Distinctiveness Maximization in Datasets Assemblage

In this paper, given a user's query set and budget, we aim to use the limited budget to help users assemble a set of datasets that can enrich a base dataset by introducing the maximum number of distinct tuples (i.e., maximizing distinctiveness). We prove this problem to be NP-hard. A greedy algorithm using exact distinctiveness computation attains an approximation ratio of (1-1/e)/2, but it lacks efficiency and scalability due to its frequent computation of the exact distinctiveness marginal gain of any candidate dataset for selection. This requires scanning through every tuple in candidate datasets and thus is unaffordable in practice. To overcome this limitation, we propose an efficient machine learning (ML)-based method for estimating the distinctiveness marginal gain of any candidate dataset. This effectively eliminates the need to test each tuple individually. Estimating the distinctiveness marginal gain of a dataset involves estimating the number of distinct tuples in the tuple sets returned by each query in a query set across multiple datasets. This can be viewed as the cardinality estimation for a query set on a set of datasets, and the proposed method is the first to tackle this cardinality estimation problem. This is a significant advancement over prior methods that were limited to single-query cardinality estimation on a single dataset and struggled with identifying overlaps among tuple sets returned by each query in a query set across multiple datasets. Extensive experiments using five real-world data pools demonstrate that our algorithm, which utilizes ML-based distinctiveness estimation, outperforms all relevant baselines in effectiveness, efficiency, and scalability. A case study on two downstream ML tasks also highlights its potential to find datasets with more useful tuples to enhance the performance of ML tasks.

cs.DB↗

arXiv2022

Influence Maximization in Real-World Closed Social Networks

In the last few years, many closed social networks such as WhatsAPP and WeChat have emerged to cater for people's growing demand of privacy and independence. In a closed social network, the posted content is not available to all users or senders can set limits on who can see the posted content. Under such a constraint, we study the problem of influence maximization in a closed social network. It aims to recommend users (not just the seed users) a limited number of existing friends who will help propagate the information, such that the seed users' influence spread can be maximized. We first prove that this problem is NP-hard. Then, we propose a highly effective yet efficient method to augment the diffusion network, which initially consists of seed users only. The augmentation is done by iteratively and intelligently selecting and inserting a limited number of edges from the original network. Through extensive experiments on real-world social networks including deployment into a real-world application, we demonstrate the effectiveness and efficiency of our proposed method.

cs.SI↗

arXiv2020

Temporal Network Representation Learning via Historical Neighborhoods Aggregation

Network embedding is an effective method to learn low-dimensional representations of nodes, which can be applied to various real-life applications such as visualization, node classification, and link prediction. Although significant progress has been made on this problem in recent years, several important challenges remain, such as how to properly capture temporal information in evolving networks. In practice, most networks are continually evolving. Some networks only add new edges or nodes such as authorship networks, while others support removal of nodes or edges such as internet data routing. If patterns exist in the changes of the network structure, we can better understand the relationships between nodes and the evolution of the network, which can be further leveraged to learn node representations with more meaningful information. In this paper, we propose the Embedding via Historical Neighborhoods Aggregation (EHNA) algorithm. More specifically, we first propose a temporal random walk that can identify relevant nodes in historical neighborhoods which have impact on edge formations. Then we apply a deep learning model which uses a custom attention mechanism to induce node embeddings that directly capture temporal information in the underlying feature representation. We perform extensive experiments on a range of real-world datasets, and the results demonstrate the effectiveness of our new approach in the network reconstruction task and the link prediction task.

cs.LG↗