arXiv subjects

Chuqin Geng

Publications and source records attributed to Chuqin Geng.

14 recordsLinked to original sources

arXiv2026

DreamProver: Evolving Transferable Lemma Libraries via a Wake-Sleep Theorem-Proving Agent

We introduce DreamProver, an agentic framework that leverages a "wake-sleep" program induction paradigm to discover reusable lemmas for formal theorem proving. Existing approaches either rely on fixed lemma libraries, which limit adaptability, or synthesize highly specific intermediate lemmas tailored to individual theorems, thereby lacking generality. DreamProver addresses this gap through an iterative two-stage process. In the wake stage, DreamProver attempts to prove theorems from a training set using the current lemma library while proposing new candidate lemmas. In the "sleep" stage, it abstracts, refines, and consolidates these candidates to compress and optimize the library. Through this alternating cycle, DreamProver progressively evolves a compact set of high-level, transferable lemmas that can be effectively used to prove unseen theorems in related domains. Experimental results demonstrate that DreamProver substantially improves proof success rates across a diverse set of mathematical benchmarks, while also producing more concise proofs and reducing computational cost.

cs.AI↗

arXiv2026

LogicXGNN: Grounded Logical Rules for Explaining Graph Neural Networks

Existing rule-based explanations for Graph Neural Networks (GNNs) provide global interpretability but often optimize and assess fidelity in an intermediate, uninterpretable concept space, overlooking grounding quality for end users in the final subgraph explanations. This gap yields explanations that may appear faithful yet be unreliable in practice. To this end, we propose LogicXGNN, a post-hoc framework that constructs logical rules over reliable predicates explicitly designed to capture the GNN's message-passing structure, thereby ensuring effective grounding. We further introduce data-grounded fidelity ($\textit{Fid}_{\mathcal{D}}$), a realistic metric that evaluates explanations in their final-graph form, along with complementary utility metrics such as coverage and validity. Across extensive experiments, LogicXGNN improves $\textit{Fid}_{\mathcal{D}}$ by over 20% on average relative to state-of-the-art methods while being 10-100 $\times$ faster. With strong scalability and utility performance, LogicXGNN produces explanations that are faithful to the model's logic and reliably grounded in observable data. Our code is available at https://github.com/allengeng123/LogicXGNN/.

cs.LG↗

arXiv2026

Neural Proposals, Symbolic Guarantees: Neuro-Symbolic Graph Generation with Hard Constraints

We challenge black-box purely deep neural approaches for molecules and graph generation, which are limited in controllability and lack formal guarantees. We introduce Neuro-Symbolic Graph Generative Modeling (NSGGM), a neurosymbolic framework that reapproaches molecule generation as a scaffold and interaction learning task with symbolic assembly. An autoregressive neural model proposes scaffolds and refines interaction signals, and a CPU-efficient SMT solver constructs full graphs while enforcing chemical validity, structural rules, and user-specific constraints, yielding molecules that are correct by construction and interpretable control that pure neural methods cannot provide. NSGGM delivers strong performance on both unconstrained generation and constrained generation tasks, demonstrating that neuro-symbolic modeling can match state-of-the-art generative performance while offering explicit controllability and guarantees. To evaluate more nuanced controllability, we also introduce a Logical-Constraint Molecular Benchmark, designed to test strict hard-rule satisfaction in workflows that require explicit, interpretable specifications together with verifiable compliance.

cs.LG↗

arXiv2026

VISIONLOGIC: From Neuron Activations to Causally Grounded Concept Rules for Vision Models

While concept-based explanations improve interpretability over local attributions, they often rely on correlational signals and lack causal validation. We introduce VisionLogic, a novel neural-symbolic framework that produces faithful, hierarchical explanations as global logical rules over causally validated concepts. VisionLogic first learns activation thresholds that abstract neuron activations into predicates, then induces class-level logical rules from these predicates. It then grounds predicates to visual concepts via ablation-based causal tests with iterative region refinement, ensuring that discovered concepts correspond to features that are causal for predicate activation. Across different vision architectures such as CNNs and ViTs, it produces interpretable concepts and compact rules that largely preserve the original model's predictive performance. In our large-scale human evaluations, VisionLogic's concept explanations significantly improve participants' understanding of model behavior over prior concept-based methods.

cs.CV↗

arXiv2026

Beyond Message Passing: A Symbolic Alternative for Expressive and Interpretable Graph Learning

Graph Neural Networks (GNNs) have become essential in high-stakes domains such as drug discovery, yet their black-box nature remains a significant barrier to trustworthiness. While self-explainable GNNs attempt to bridge this gap, they often rely on standard message-passing backbones that inherit fundamental limitations, including the 1-Weisfeiler-Lehman (1-WL) expressivity barrier and a lack of fine-grained interpretability. To address these challenges, we propose SymGraph, a symbolic framework designed to transcend these constraints. By replacing continuous message passing with discrete structural hashing and topological role-based aggregation, our architecture theoretically surpasses the 1-WL barrier, achieving superior expressiveness without the overhead of differentiable optimization. Extensive empirical evaluations demonstrate that SymGraph achieves state-of-the-art performance, outperforming existing self-explainable GNNs. Notably, SymGraph delivers 10x to 100x speedups in training time using only CPU execution. Furthermore, SymGraph generates rules with superior semantic granularity compared to existing rule-based methods, offering great potential for scientific discovery and explainable AI.

cs.LG↗

arXiv2025

NEUROLOGIC: From Neural Representations to Interpretable Logic Rules

Rule-based explanation methods offer rigorous and globally interpretable insights into neural network behavior. However, existing approaches are mostly limited to small fully connected networks and depend on costly layerwise rule extraction and substitution processes. These limitations hinder their generalization to more complex architectures such as Transformers. Moreover, existing methods produce shallow, decision-tree-like rules that fail to capture rich, high-level abstractions in complex domains like computer vision and natural language processing. To address these challenges, we propose NEUROLOGIC, a novel framework that extracts interpretable logical rules directly from deep neural networks. Unlike previous methods, NEUROLOGIC can construct logic rules over hidden predicates derived from neural representations at any chosen layer, in contrast to costly layerwise extraction and rewriting. This flexibility enables broader architectural compatibility and improved scalability. Furthermore, NEUROLOGIC supports richer logical constructs and can incorporate human prior knowledge to ground hidden predicates back to the input space, enhancing interpretability. We validate NEUROLOGIC on Transformer-based sentiment analysis, demonstrating its ability to extract meaningful, interpretable logic rules and provide deeper insights-tasks where existing methods struggle to scale.

cs.LG↗

arXiv2025

Learning Minimal Neural Specifications

Formal verification is only as good as the specification of a system, which is also true for neural network verification. Existing specifications follow the paradigm of data as specification, where the local neighborhood around a reference data point is considered correct or robust. While these specifications provide a fair testbed for assessing model robustness, they are too restrictive for verifying any unseen test data points, a challenging task with significant real-world implications. Recent work shows great promise through a new paradigm, neural representation as specification, which uses neural activation patterns (NAPs) for this purpose. However, it computes the most refined NAPs, which include many redundant neurons. In this paper, we study the following problem: Given a neural network, find a minimal (general) NAP specification that is sufficient for formal verification of its robustness properties. Finding the minimal NAP specification not only expands verifiable bounds but also provides insights into which set of neurons contributes to the model's robustness. To address this problem, we propose three approaches: conservative, statistical, and optimistic. Each of these methods offers distinct strengths and trade-offs in terms of minimality and computational speed, making them suitable for scenarios with different priorities. Notably, the optimistic approach can probe potential causal links between neurons and the robustness of large vision neural networks without relying on verification tools, a task existing methods struggle to scale. Our experiments show that minimal NAP specifications use far fewer neurons than those from previous work while expanding verifiable boundaries by several orders of magnitude.

cs.LG↗

arXiv2024

SAT-DIFF: A Tree Diffing Framework Using SAT Solving

Computing differences between tree-structured data is a critical but challenging problem in software analysis. In this paper, we propose a novel tree diffing approach called SatDiff, which reformulates the structural diffing problem into a MaxSAT problem. By encoding the necessary transformations from the source tree to the target tree, SatDiff generates correct, minimal, and type safe low-level edit scripts with formal guarantees. We then synthesize concise high-level edit scripts by effectively merging low-level edits in the appropriate topological order. Our empirical results demonstrate that SatDiff outperforms existing heuristic-based approaches by a significant margin in terms of conciseness while maintaining a reasonable runtime.

cs.PL↗

arXiv2023

TorchProbe: Fuzzing Dynamic Deep Learning Compilers

Static and dynamic computational graphs represent two distinct approaches to constructing deep learning frameworks. The former prioritizes compiler-based optimizations, while the latter focuses on programmability and user-friendliness. The recent release of PyTorch 2.0, which supports compiling arbitrary deep learning programs in Python, signifies a new direction in the evolution of deep learning infrastructure to incorporate compiler techniques in a more dynamic manner and support more dynamic language features like dynamic control flows and closures. Given PyTorch's seamless integration with Python, its compiler aims to support arbitrary deep learning code written in Python. However, the inherent dynamism of Python poses challenges to the completeness and robustness of the compiler. While recent research has introduced fuzzing to test deep learning compilers, there is still a lack of comprehensive analysis on how to test dynamic features. To address this issue, we propose several code transformations to generate test cases involving dynamic features. These transformations preserve the program's semantics, ensuring that any discrepancy between the transformed and original programs indicates the presence of a bug. Through our approach, we have successfully identified twenty previously unknown bugs in the PyTorch compiler and its underlying tensor compiler Triton.

cs.SE↗

arXiv2023

Scalar Invariant Networks with Zero Bias

Just like weights, bias terms are the learnable parameters of many popular machine learning models, including neural networks. Biases are thought to enhance the representational power of neural networks, enabling them to solve a variety of tasks in computer vision. However, we argue that biases can be disregarded for some image-related tasks such as image classification, by considering the intrinsic distribution of images in the input space and desired model properties from first principles. Our findings suggest that zero-bias neural networks can perform comparably to biased networks for practical image classification tasks. We demonstrate that zero-bias neural networks possess a valuable property called scalar (multiplication) invariance. This means that the prediction of the network remains unchanged when the contrast of the input image is altered. We extend scalar invariance to more general cases, enabling formal verification of certain convex regions of the input space. Additionally, we prove that zero-bias neural networks are fair in predicting the zero image. Unlike state-of-the-art models that may exhibit bias toward certain labels, zero-bias networks have uniform belief in all labels. We believe dropping bias terms can be considered as a geometric prior in designing neural network architecture for image classification, which shares the spirit of adapting convolutions as the transnational invariance prior. The robustness and fairness advantages of zero-bias neural networks may also indicate a promising path towards trustworthy and ethical AI.

cs.CV↗

arXiv2023

Can ChatGPT Pass An Introductory Level Functional Language Programming Course?

The recent introduction of ChatGPT has drawn significant attention from both industry and academia due to its impressive capabilities in solving a diverse range of tasks, including language translation, text summarization, and computer programming. Its capability for writing, modifying, and even correcting code together with its ease of use and access is already dramatically impacting computer science education. This paper aims to explore how well ChatGPT can perform in an introductory-level functional language programming course. In our systematic evaluation, we treated ChatGPT as one of our students and demonstrated that it can achieve a grade B- and its rank in the class is 155 out of 314 students overall. Our comprehensive evaluation provides valuable insights into ChatGPT's impact from both student and instructor perspectives. Additionally, we identify several potential benefits that ChatGPT can offer to both groups. Overall, we believe that this study significantly clarifies and advances our understanding of ChatGPT's capabilities and potential impact on computer science education.

cs.CY↗

arXiv2023

Towards Reliable Neural Specifications

Having reliable specifications is an unavoidable challenge in achieving verifiable correctness, robustness, and interpretability of AI systems. Existing specifications for neural networks are in the paradigm of data as specification. That is, the local neighborhood centering around a reference input is considered to be correct (or robust). While existing specifications contribute to verifying adversarial robustness, a significant problem in many research domains, our empirical study shows that those verified regions are somewhat tight, and thus fail to allow verification of test set inputs, making them impractical for some real-world applications. To this end, we propose a new family of specifications called neural representation as specification, which uses the intrinsic information of neural networks - neural activation patterns (NAPs), rather than input data to specify the correctness and/or robustness of neural network predictions. We present a simple statistical approach to mining neural activation patterns. To show the effectiveness of discovered NAPs, we formally verify several important properties, such as various types of misclassifications will never happen for a given NAP, and there is no ambiguity between different NAPs. We show that by using NAP, we can verify a significant region of the input space, while still recalling 84% of the data on MNIST. Moreover, we can push the verifiable bound to 10 times larger on the CIFAR10 benchmark. Thus, we argue that NAPs can potentially be used as a more reliable and extensible specification for neural network verification.

cs.LG↗

arXiv2023

Identifying Different Student Clusters in Functional Programming Assignments: From Quick Learners to Struggling Students

Instructors and students alike are often focused on the grade in programming assignments as a key measure of how well a student is mastering the material and whether a student is struggling. This can be, however, misleading. Especially when students have access to auto-graders, their grades may be heavily skewed. In this paper, we analyze student assignment submission data collected from a functional programming course taught at McGill university incorporating a wide range of features. In addition to the grade, we consider activity time data, time spent, and the number of static errors. This allows us to identify four clusters of students: "Quick-learning", "Hardworking", "Satisficing", and "Struggling" through cluster algorithms. We then analyze how work habits, working duration, the range of errors, and the ability to fix errors impact different clusters of students. This structured analysis provides valuable insights for instructors to actively help different types of students and emphasize different aspects of their overall course design. It also provides insights for students themselves to understand which aspects they still struggle with and allows them to seek clarification and adjust their work habits.

cs.CY↗

arXiv2022

Novice Type Error Diagnosis with Natural Language Models

Strong static type systems help programmers eliminate many errors without much burden of supplying type annotations. However, this flexibility makes it highly non-trivial to diagnose ill-typed programs, especially for novice programmers. Compared to classic constraint solving and optimization-based approaches, the data-driven approach has shown great promise in identifying the root causes of type errors with higher accuracy. Instead of relying on hand-engineered features, this work explores natural language models for type error localization, which can be trained in an end-to-end fashion without requiring any features. We demonstrate that, for novice type error diagnosis, the language model-based approach significantly outperforms the previous state-of-the-art data-driven approach. Specifically, our model could predict type errors correctly 62% of the time, outperforming the state-of-the-art Nate's data-driven model by 11%, in a more rigorous accuracy metric. Furthermore, we also apply structural probes to explain the performance difference between different language models.

cs.PL↗