arXiv subjects

Zaiwen Feng

Publications and source records attributed to Zaiwen Feng.

At least 19 recordsLinked to original sources

arXiv2026

LightAVSeg: Lightweight Audio-Visual Segmentation

Audio-Visual Segmentation (AVS) targets pixel level localization of sounding emitting objects in videos. However, existing models rely on dense cross-modal attention with quadratic computational cost, limiting their suitability for resource efficient deployment. Most efficiency oriented methods focus on backbone reduction and overlook the interaction module as the primary bottleneck. This paper proposes LightAVSeg, a lightweight framework that replaces heavy attention with a decoupled design for semantic filtering and spatial grounding, resulting in interaction costs that scale linearly with spatial resolution. Furthermore, we introduce an auxiliary alignment loss to enforce semantic consistency during training with zero inference overhead. Extensive experiments demonstrate that LightAVSeg achieves a new state-of-the-art among lightweight methods: with 20.5M parameters ~1/7 of AVSegFormer), it reaches 50.4 mIoU on the MS3 benchmark and enables efficient inference on a mobile processor.

cs.CV↗

arXiv2026

MetaToolAgent: Towards Generalizable Tool Usage in LLMs through Meta-Learning

Tool learning is increasingly important for large language models (LLMs) to effectively coordinate and utilize a diverse set of tools in order to solve complex real-world tasks. By selecting and integrating appropriate tools, LLMs extend their capabilities beyond pure language understanding to perform specialized functions. However, existing methods for tool selection often focus on limited tool sets and struggle to generalize to novel tools encountered in practical deployments. To address these challenges, we introduce a comprehensive dataset spanning 7 domains, containing 155 tools and 9,377 question-answer pairs, which simulates realistic integration scenarios. Additionally, we propose MetaToolAgent (MTA), a meta-learning approach designed to improve cross-tool generalization. Experimental results show that MTA significantly outperforms baseline methods on unseen tools, demonstrating its promise for building flexible and scalable systems that require dynamic tool coordination.

cs.LG↗

arXiv2026

XLinear: A Lightweight and Accurate MLP-Based Model for Long-Term Time Series Forecasting with Exogenous Inputs

Despite the prevalent assumption of uniform variable importance in long-term time series forecasting models, real world applications often exhibit asymmetric causal relationships and varying data acquisition costs. Specifically, cost-effective exogenous data (e.g., local weather) can unilaterally influence dynamics of endogenous variables, such as lake surface temperature. Exploiting these links enables more effective forecasts when exogenous inputs are readily available. Transformer-based models capture long-range dependencies but incur high computation and suffer from permutation invariance. Patch-based variants improve efficiency yet can miss local temporal patterns. To efficiently exploit informative signals across both the temporal dimension and relevant exogenous variables, this study proposes XLinear, a lightweight time series forecasting model built upon MultiLayer Perceptrons (MLPs). XLinear uses a global token derived from an endogenous variable as a pivotal hub for interacting with exogenous variables, and employs MLPs with sigmoid activation to extract both temporal patterns and variate-wise dependencies. Its prediction head then integrates these signals to forecast the endogenous series. We evaluate XLinear on seven standard benchmarks and five real-world datasets with exogenous inputs. Compared with state-of-the-art models, XLinear delivers superior accuracy and efficiency for both multivariate forecasts and univariate forecasts influenced by exogenous inputs.

cs.LG↗

arXiv2025

FastER: On-Demand Entity Resolution in Property Graphs

Entity resolution (ER) is the problem of identifying and linking database records that refer to the same real-world entity. Traditional ER methods use batch processing, which becomes impractical with growing data volumes due to high computational costs and lack of real-time capabilities. In many applications, users need to resolve entities for only a small portion of their data, making full data processing unnecessary -- a scenario known as "ER-on-demand". This paper proposes FastER, an efficient ER-on-demand framework for property graphs. Our approach uses graph differential dependencies (GDDs) as a knowledge encoding language to design effective filtering mechanisms that leverage both structural and attribute semantics of graphs. We construct a blocking graph from filtered subgraphs to reduce the number of candidate entity pairs requiring comparison. Additionally, FastER incorporates Progressive Profile Scheduling (PPS), allowing the system to incrementally produce results throughout the resolution process. Extensive evaluations on multiple benchmark datasets demonstrate that FastER significantly outperforms state-of-the-art ER methods in computational efficiency and real-time processing for on-demand tasks while ensuring reliability. We make FastER publicly available at: https://anonymous.4open.science/r/On_Demand_Entity_Resolution-9DFB

cs.DB↗

arXiv2025

Unbiased Reasoning for Knowledge-Intensive Tasks in Large Language Models via Conditional Front-Door Adjustment

Large Language Models (LLMs) have shown impressive capabilities in natural language processing but still struggle to perform well on knowledge-intensive tasks that require deep reasoning and the integration of external knowledge. Although methods such as Retrieval-Augmented Generation (RAG) and Chain-of-Thought (CoT) have been proposed to enhance LLMs with external knowledge, they still suffer from internal bias in LLMs, which often leads to incorrect answers. In this paper, we propose a novel causal prompting framework, Conditional Front-Door Prompting (CFD-Prompting), which enables the unbiased estimation of the causal effect between the query and the answer, conditional on external knowledge, while mitigating internal bias. By constructing counterfactual external knowledge, our framework simulates how the query behaves under varying contexts, addressing the challenge that the query is fixed and is not amenable to direct causal intervention. Compared to the standard front-door adjustment, the conditional variant operates under weaker assumptions, enhancing both robustness and generalisability of the reasoning process. Extensive experiments across multiple LLMs and benchmark datasets demonstrate that CFD-Prompting significantly outperforms existing baselines in both accuracy and robustness.

cs.CL↗

arXiv2025

An LLM Agent-Based Complex Semantic Table Annotation Approach

The Semantic Table Annotation (STA) task, which includes Column Type Annotation (CTA) and Cell Entity Annotation (CEA), maps table contents to ontology entities and plays important roles in various semantic applications. However, complex tables often pose challenges such as semantic loss of column names or cell values, strict ontological hierarchy requirements, homonyms, spelling errors, and abbreviations, which hinder annotation accuracy. To address these issues, this paper proposes an LLM-based agent approach for CTA and CEA. We design and implement five external tools with tailored prompts based on the ReAct framework, enabling the STA agent to dynamically select suitable annotation strategies depending on table characteristics. Experiments are conducted on the Tough Tables and BiodivTab datasets from the SemTab challenge, which contain the aforementioned challenges. Our method outperforms existing approaches across various metrics. Furthermore, by leveraging Levenshtein distance to reduce redundant annotations, we achieve a 70% reduction in time costs and a 60% reduction in LLM token usage, providing an efficient and cost-effective solution for STA.

cs.CL↗

arXiv2025

RAE: A Rule-Driven Approach for Attribute Embedding in Property Graph Recommendation

Recommendation systems are crucial in modern applications to enhance the user experience and drive business conversion rates through personalization. However, insufficient utilization of attribute information within the property graph remains a significant challenge. Most existing graph convolutional network (GCN) models do not consider attribute information, and those that do often employ a simplified triple format , which fails to fully exploit the rich semantic structures of property graphs necessary for effective recommendations. To overcome these limitations, we introduce Rule-Driven Approach for Attribute Embedding (RAE), a novel methodology that enhances recommendation performance by effectively mining and utilizing semantic rules from property graphs. RAE applies a rule-mining process to extract meaningful rules that guide random walks in generating enriched attribute embeddings. These enriched embeddings are subsequently integrated into GCNs, surpassing conventional triple-based embedding techniques. We evaluate RAE on real-world datasets (e.g., Blogcatalog and Flickr) and demonstrate that RAE achieves an average improvement of 10.6% in both Recall@20 and NDCG@20 compared to state-of-the-art baselines, indicating superior relevance coverage and ranking rationality in top-20 recommendations. Additionally, RAE exhibits enhanced robustness against data sparsity and the attribute missingness problem. Our novel approach underscores the significant performance gains achieved in recommendation systems by fully leveraging attribute information within property graphs, enhancing both effectiveness and reliability.

cs.IR↗

arXiv2025

Knowledge prompt chaining for semantic modeling

The task of building semantics for structured data such as CSV, JSON, and XML files is highly relevant in the knowledge representation field. Even though we have a vast of structured data on the internet, mapping them to domain ontologies to build semantics for them is still very challenging as it requires the construction model to understand and learn graph-structured knowledge. Otherwise, the task will require human beings' effort and cost. In this paper, we proposed a novel automatic semantic modeling framework: Knowledge Prompt Chaining. It can serialize the graph-structured knowledge and inject it into the LLMs properly in a Prompt Chaining architecture. Through this knowledge injection and prompting chaining, the model in our framework can learn the structure information and latent space of the graph and generate the semantic labels and semantic graphs following the chains' insturction naturally. Based on experimental results, our method achieves better performance than existing leading techniques, despite using reduced structured input data.

cs.CL↗

arXiv2024

Counterfactual Samples Constructing and Training for Commonsense Statements Estimation

Plausibility Estimation (PE) plays a crucial role for enabling language models to objectively comprehend the real world. While large language models (LLMs) demonstrate remarkable capabilities in PE tasks but sometimes produce trivial commonsense errors due to the complexity of commonsense knowledge. They lack two key traits of an ideal PE model: a) Language-explainable: relying on critical word segments for decisions, and b) Commonsense-sensitive: detecting subtle linguistic variations in commonsense. To address these issues, we propose a novel model-agnostic method, referred to as Commonsense Counterfactual Samples Generating (CCSG). By training PE models with CCSG, we encourage them to focus on critical words, thereby enhancing both their language-explainable and commonsense-sensitive capabilities. Specifically, CCSG generates counterfactual samples by strategically replacing key words and introducing low-level dropout within sentences. These counterfactual samples are then incorporated into a sentence-level contrastive training framework to further enhance the model's learning process. Experimental results across nine diverse datasets demonstrate the effectiveness of CCSG in addressing commonsense reasoning challenges, with our CCSG method showing 3.07% improvement against the SOTA methods.

cs.CL↗

arXiv2024

A Heterogeneous Network-based Contrastive Learning Approach for Predicting Drug-Target Interaction

Drug-target interaction (DTI) prediction is crucial for drug development and repositioning. Methods using heterogeneous graph neural networks (HGNNs) for DTI prediction have become a promising approach, with attention-based models often achieving excellent performance. However, these methods typically overlook edge features when dealing with heterogeneous biomedical networks. We propose a heterogeneous network-based contrastive learning method called HNCL-DTI, which designs a heterogeneous graph attention network to predict potential/novel DTIs. Specifically, our HNCL-DTI utilizes contrastive learning to collaboratively learn node representations from the perspective of both node-based and edge-based attention within the heterogeneous structure of biomedical networks. Experimental results show that HNCL-DTI outperforms existing advanced baseline methods on benchmark datasets, demonstrating strong predictive ability and practical effectiveness. The data and source code are available at https://github.com/Zaiwen/HNCL-DTI.

q-bio.BM↗

arXiv2024

When GDD meets GNN: A Knowledge-driven Neural Connection for Effective Entity Resolution in Property Graphs

This paper studies the entity resolution (ER) problem in property graphs. ER is the task of identifying and linking different records that refer to the same real-world entity. It is commonly used in data integration, data cleansing, and other applications where it is important to have accurate and consistent data. In general, two predominant approaches exist in the literature: rule-based and learning-based methods. On the one hand, rule-based techniques are often desired due to their explainability and ability to encode domain knowledge. Learning-based methods, on the other hand, are preferred due to their effectiveness in spite of their black-box nature. In this work, we devise a hybrid ER solution, GraphER, that leverages the strengths of both systems for property graphs. In particular, we adopt graph differential dependency (GDD) for encoding the so-called record-matching rules, and employ them to guide a graph neural network (GNN) based representation learning for the task. We conduct extensive empirical evaluation of our proposal on benchmark ER datasets including 17 graph datasets and 7 relational datasets in comparison with 10 state-of-the-art (SOTA) techniques. The results show that our approach provides a significantly better solution to addressing ER in graph data, both quantitatively and qualitatively, while attaining highly competitive results on the benchmark relational datasets w.r.t. the SOTA solutions.

cs.DB↗

arXiv2024

Causal Effect Estimation using identifiable Variational AutoEncoder with Latent Confounders and Post-Treatment Variables

Estimating causal effects from observational data is challenging, especially in the presence of latent confounders. Much work has been done on addressing this challenge, but most of the existing research ignores the bias introduced by the post-treatment variables. In this paper, we propose a novel method of joint Variational AutoEncoder (VAE) and identifiable Variational AutoEncoder (iVAE) for learning the representations of latent confounders and latent post-treatment variables from their proxy variables, termed CPTiVAE, to achieve unbiased causal effect estimation from observational data. We further prove the identifiability in terms of the representation of latent post-treatment variables. Extensive experiments on synthetic and semi-synthetic datasets demonstrate that the CPTiVAE outperforms the state-of-the-art methods in the presence of latent confounders and post-treatment variables. We further apply CPTiVAE to a real-world dataset to show its potential application.

cs.LG↗

arXiv2023

Disentangled Latent Representation Learning for Tackling the Confounding M-Bias Problem in Causal Inference

In causal inference, it is a fundamental task to estimate the causal effect from observational data. However, latent confounders pose major challenges in causal inference in observational data, for example, confounding bias and M-bias. Recent data-driven causal effect estimators tackle the confounding bias problem via balanced representation learning, but assume no M-bias in the system, thus they fail to handle the M-bias. In this paper, we identify a challenging and unsolved problem caused by a variable that leads to confounding bias and M-bias simultaneously. To address this problem with co-occurring M-bias and confounding bias, we propose a novel Disentangled Latent Representation learning framework for learning latent representations from proxy variables for unbiased Causal effect Estimation (DLRCE) from observational data. Specifically, DLRCE learns three sets of latent representations from the measured proxy variables to adjust for the confounding bias and M-bias. Extensive experiments on both synthetic and three real-world datasets demonstrate that DLRCE significantly outperforms the state-of-the-art estimators in the case of the presence of both confounding bias and M-bias.

cs.LG↗

arXiv2023

Causal Intervention for Measuring Confidence in Drug-Target Interaction Prediction

Identifying and discovering drug-target interactions(DTIs) are vital steps in drug discovery and development. They play a crucial role in assisting scientists in finding new drugs and accelerating the drug development process. Recently, knowledge graph and knowledge graph embedding (KGE) models have made rapid advancements and demonstrated impressive performance in drug discovery. However, such models lack authenticity and accuracy in drug target identification, leading to an increased misjudgment rate and reduced drug development efficiency. To address these issues, we focus on the problem of drug-target interactions, with knowledge mapping as the core technology. Specifically, a causal intervention-based confidence measure is employed to assess the triplet score to improve the accuracy of the drug-target interaction prediction model. Experimental results demonstrate that the developed confidence measurement method based on causal intervention can significantly enhance the accuracy of DTI link prediction, particularly for high-precision models. The predicted results are more valuable in guiding the design and development of subsequent drug development experiments, thereby significantly improving the efficiency of drug development.

q-bio.QM↗

arXiv2023

An Efficient Approach for Discovering Graph Entity Dependencies (GEDs)

Graph entity dependencies (GEDs) are novel graph constraints, unifying keys and functional dependencies, for property graphs. They have been found useful in many real-world data quality and data management tasks, including fact checking on social media networks and entity resolution. In this paper, we study the discovery problem of GEDs -- finding a minimal cover of valid GEDs in a given graph data. We formalise the problem, and propose an effective and efficient approach to overcome major bottlenecks in GED discovery. In particular, we leverage existing graph partitioning algorithms to enable fast GED-scope discovery, and employ effective pruning strategies over the prohibitively large space of candidate dependencies. Furthermore, we define an interestingness measure for GEDs based on the minimum description length principle, to score and rank the mined cover set of GEDs. Finally, we demonstrate the scalability and effectiveness of our GED discovery approach through extensive experiments on real-world benchmark graph data sets; and present the usefulness of the discovered rules in different downstream data quality management applications.

cs.DB↗

arXiv2023

FASTAGEDS: Fast Approximate Graph Entity Dependency Discovery

This paper studies the discovery of approximate rules in property graphs. We propose a semantically meaningful measure of error for mining graph entity dependencies (GEDs) at almost hold, to tolerate errors and inconsistencies that exist in real-world graphs. We present a new characterisation of GED satisfaction, and devise a depth-first search strategy to traverse the search space of candidate rules efficiently. Further, we perform experiments to demonstrate the feasibility and scalability of our solution, FASTAGEDS, with three real-world graphs.

cs.DB↗

arXiv2023

BPCE: A Prototype for Co-Evolution between Business Process Variants through Configurable Process Model

With the continuous development of business process management technology, the increasing business process models are usually owned by large enterprises. In large enterprises, different stakeholders may modify the same business process model. In order to better manage the changeability of processes, they adopt configurable business process models to manage process variants. However, the process variants will vary with the change in enterprise business demands. Therefore, it is necessary to explore the co-evolution of the process variants so as to effectively manage the business process family. To this end, a novel framework for co-evolution between business process variants through a configurable process model is proposed in this work. First, the mapping relationship between process variants and configurable models is standardized in this study. A series of change operations and change propagation operations between process variants and configurable models are further defined for achieving propagation. Then, an overall algorithm is proposed for achieving co-evolution of process variants. Next, a prototype is developed for managing change synchronization between process variants and configurable process models. Finally, the effectiveness and efficiency of our proposed process change propagation method are verified based on experiments on two business process datasets. The experimental results show that our approach implements the co-evolution of process variants with high accuracy and efficiency.

cs.SE↗

arXiv2023

SGMFQP:An Ontology-based Swine Gut Microbiota Federated Query Platform

Gut microbiota plays a crucial role in modulating pig development and health, and gut microbiota characteristics are associated with differences in feed efficiency. To answer open questions in feed efficiency analysis, biologists seek to retrieve information across multiple heterogeneous data sources. However, this is error-prone and time-consuming work since the queries can involve a sequence of multiple sub-queries over several databases. We present an implementation of an ontology-based Swine Gut Microbiota Federated Query Platform (SGMFQP) that provides a convenient, automated, and efficient query service about swine feeding and gut microbiota. The system is constructed based on a domain-specific Swine Gut Microbiota Ontology (SGMO), which facilitates the construction of queries independent of the actual organization of the data in the individual sources. This process is supported by a template-based query interface. A Datalog+-based federated query engine transforms the queries into sub-queries tailored for each individual data source, and an automated workflow orchestration mechanism executes the queries in each source database and consolidates the results. The efficiency of the system is demonstrated on several swine feeding scenarios.

cs.DB↗