6 March 2023 in IEEE Transactions on Neural Networks and Learning Systems
Recent years have witnessed the proliferation of techniques for streaming data mining to meet the demands of many real-time systems, where high-dimensional streaming data are generated at high speed, increasing the burden on both hardware and software. Some feature selection algorithms for streaming data are proposed to tackle this issue. However, these algorithms do not consider the distribution shift due to nonstationary scenarios, leading to performance degradation when the underlying distribution changes in the data stream. To solve this problem, this article investigates feature selection in streaming data through incremental Markov boundary (MB) learning and proposes a novel algorithm. Different from existing algorithms focusing on prediction performance on off-line data, the MB is learned by analyzing conditional dependence/independence in data, which uncovers the underlying mechanism and is naturally more robust against the distribution shift. To learn MB in the data stream, the proposal transforms the learned information in previous data blocks to prior knowledge and employs them to assist MB discovery in current data blocks, where the likelihood of distribution shift and reliability of conditional independence test are monitored to avoid the negative impact from invalid prior information. Extensive experiments on synthetic and real-world datasets demonstrate the superiority of the proposed algorithm.
13 January 2025 in IEEE Transactions on Knowledge and Data Engineering
Traditional domain-specific causal discovery relies on expert knowledge to guide the data-based structure learning process, thereby improving the reliability of recovered causality. Recent studies have shown promise in using the Large Language Model (LLM) as causal experts to construct autonomous expert-guided causal discovery systems through causal reasoning between pairwise variables. However, their performance is hampered by inaccuracies in aligning LLM-derived causal knowledge with the actual causal structure. To address this issue, this paper proposes a novel LLM-driven causal discovery framework that limits LLM’s prior within a reliable range. Instead of pairwise causal reasoning that requires both precise and comprehensive output results, the LLM is directed to focus on each single aspect separately. By combining these distinct causal insights, a unified set of structural constraints is created, termed a harmonized prior, which draws on their respective strengths to ensure prior accuracy. On this basis, we introduce plug-and-play integrations of the harmonized prior into mainstream categories of structure learning methods, thereby enhancing their applicability in practical scenarios. Evaluations on real-world data demonstrate the effectiveness of our approach.
4 February 2025 in IEEE Transactions on Knowledge and Data Engineering
Causal discovery faces significant challenges as the number of hypotheses grows exponentially with the number of variables. This complexity becomes particularly daunting when dealing with large sets of variables. We introduce a novel divide-and-conquer method that uniquely handles this challenge. The existing division strategies often rely on conditional independency (CI) tests or data-driven clustering to split variables, which can suffer from the typical data scarcity in large-scale settings, thus leading to inaccurate division results. The proposed method overcomes this by implementing a data-independent division strategy, which constructs a prior structure, informed by potential causal relationships identified using a Large Language Model (LLM), to guide recursively dividing variables into sub-sets. This approach avoids the impact of data insufficiency and is robust against potential incompleteness in the prior structure. In the merging phase, we adopt a score-based refinement strategy to address fake causal links caused by hidden variables in sub-sets, which eliminates edges in the intersected parts of sub-sets to optimize the score of local structures. While maintaining both correctness and completeness under the faithfulness assumption, this novel merging approach demonstrates enhanced performance than the conventional CI-test based merging strategy in practical scenarios. Empirical evaluations on various large-scale datasets demonstrate the proposed approach's superior accuracy and efficiency compared to existing causal discovery methods.
4 July 2022 in IEEE Transactions on Neural Networks and Learning Systems
The evaluation of knowledge quality (KQ) in multisource knowledge graphs (KGs) is an essential step for many applications, such as fragmented knowledge fusion and knowledge base construction. Many existing quality evaluation methods for multisource knowledge are based on validation from high-quality knowledge bases or statistical analysis of knowledge related to a specific fact from multiple sources, named external consistency (EC)-based methods. However, high-quality KGs are difficult to obtain, and there might exist incorrect knowledge in multisource KGs interfering with KQ evaluation. To address the issue, this article refers to the internal structure of a KG to evaluate the degree to which the contained triples conform to the overall semantic pattern of the KG, such as KG embedding and logic inference-based approaches, defined as internal consistency (IC) evaluation. The IC is integrated with the EC to identify possible incorrect triples and reduce their influences on the KQ evaluation, thus alleviating the interference of incorrect knowledge. The proposed method is verified with multiple datasets, and the results demonstrate that the proposed method could significantly reduce wrong evaluations caused by incorrect knowledge and effectively improve the quality evaluation of triples.
1 February 2023 in IEEE Transactions on Geoscience and Remote Sensing
The Remote Sensing (RS) field has an increasing research interest in using deep learning (DL) models to recognize kinds of RS data, leading to a great demand for training data annotation. Due to the high cost of expertise, employing non-experts to label data has become an important way to improve labeling efficiency. Commonly, a single data sample is labeled by multiple annotators and the most voted label is accepted to promise accuracy. But in the RS context, the widely admitted strategy could lose effect. Usually RS data involves considerable classes on account of the complexity of surface environments, which is prone to inter-class similarity difficult to distinguish. Annotators without expertise probably make mistakes on these indistinguishable classes, thus causing error voted labels. Although classification of different characteristics in RS data have been widely documented, the non-expert annotators are unfamiliar with these expertise, and it is difficult to force them to handle specialized labeling skills. To address the issues, this paper bases multi-annotator label selection on the investigation of annotators’ own ability in distinguishing similar classes of images. A quality evaluation process is designed which weights the labels from capable annotators higher than those from weak ones. By a multi-round quality evaluation algorithm, correct labels could out-compete the wrong ones even disadvantaged in numbers. Experimental results demonstrate the advance of the proposed method on RS datasets.
16 December 2024 in IEEE Robotics and Automation Letters
Trajectory generation is a pivotal task in autonomous driving. Recent studies have introduced the autoregressive paradigm, leveraging the state transition model to approximate future trajectory distributions. This paradigm closely mirrors the real-world trajectory generation process and has achieved notable success. However, its potential is limited by the ineffective representation of realistic trajectories within the redundant state space. To address this limitation, we propose the Kinematic-Driven Generative Model for Realistic Agent Simulation (KiGRAS). Instead of modeling in the state space, KiGRAS factorizes the driving scene into action probability distributions at each time step, providing a compact space to represent realistic driving patterns. By establishing physical causality from actions (cause) to trajectories (effect) through the kinematic model, KiGRAS eliminates massive redundant trajectories. All states derived from actions in the causal space are constrained to be physically feasible. Furthermore, redundant trajectories representing identical action sequences are mapped to the same representation, reflecting their underlying actions. This approach significantly reduces task complexity and ensures physical feasibility. KiGRAS achieves state-of-the-art performance in Waymo's SimAgents Challenge, ranking first on the WOMD leaderboard with significantly fewer parameters than other models.