Causality-Driven Interpretation and Inspection of Deep Learning Systems

The Hong Kong University of Science and Technology
Department of Computer Science and Engineering


PhD Thesis Defence


Title: "Causality-Driven Interpretation and Inspection of Deep Learning Systems"

By

Mr. Zhenlan JI


Abstract:

In recent years, deep learning models have achieved outstanding performance
across diverse domains, but their complexity, black-box logic, and non-
determinism pose serious challenges for trust and interpretability. The
tremendous number of parameters and intricate architectures make formal
correctness guarantees impractical. For another, conventional testing or
interpretation techniques often rely on correlational heuristics that can be
misled by spurious relationships inherent in data. Causality, however,
offers a promising paradigm for addressing these issues, providing systematic
tools to disentangle confounding relationships and analyze how deliberate
interventions in inputs or models in the system affect outcomes.

In response, this thesis proposes a series of causality-driven frameworks
for interpreting and inspecting deep learning systems across different
scenarios and granularity levels. First, a novel causality-based test
coverage criterion is introduced: by modeling a neural network as a
structured causal graph, this criterion quantifies how well a test suite
exercises the inferred causal relations among neurons, capturing
interactions that standard coverage metrics overlook. Second, a causal
trade-off analysis framework is developed for fairness, accuracy, and
robustness. All of these metrics are treated as variables in a causal graph,
and then causal discovery is applied to learn their relationships. After
that, users can pose counterfactual queries, which are automatically
translated into interventions with standard causal inference, thereby
enabling them to understand how fairness, accuracy, and robustness interact.
Third, a causal interpretation pipeline is designed for large language model
code generation: by extracting interpretable features from prompts and
generated code, and by systematically rephrasing prompts to introduce
controlled variations, the pipeline learns how variations in prompt
characteristics causally affect properties of the generated code. These
methods are applied in diverse contexts, including DNN testing, fairness
evaluation, and prompt engineering, demonstrating that causality yields
systematic, explainable insights into deep learning systems. Overall, these
contributions advance the foundations of trustworthy AI and software
engineering by providing principled, scalable causal tools for interpreting
and inspecting deep learning systems.


Date:                   Tuesday, 2 December 2025

Time:                   9:00am - 11:00am

Venue:                  Room 3494
                        Lifts 25/26

Chairman:               Prof. Xiangtong QI (IEDA)

Committee Members:      Dr. Shuai WANG (Supervisor)
                        Prof. Raymond WONG
                        Dr. Chaojian LI
                        Prof. Jun ZHANG (ECE)
                        Prof. Shangce GAO (University of Toyama)