NeuroSymActive: Differentiable Neural-Symbolic Reasoning with Active Exploration for Knowledge Graph Question Answering

TL;DR

NeuroSymActive is a modular framework that combines a differentiable neural-symbolic reasoning layer with an active, value-guided exploration controller for Knowledge Graph Question Answering, and couples soft-unification style symbolic modules with a neural path evaluator and a Monte-Carlo style exploration policy that prioritizes high-value path expansions.

Abstract

Large pretrained language models and neural reasoning systems have advanced many natural language tasks, yet they remain challenged by knowledge-intensive queries that require precise, structured multi-hop inference. Knowledge graphs provide a compact symbolic substrate for factual grounding, but integrating graph structure with neural models is nontrivial: naively embedding graph facts into prompts leads to inefficiency and fragility, while purely symbolic or search-heavy approaches can be costly in retrievals and lack gradient-based refinement. We introduce NeuroSymActive, a modular framework that combines a differentiable neural-symbolic reasoning layer with an active, value-guided exploration controller for Knowledge Graph Question Answering. The method couples soft-unification style symbolic modules with a neural path evaluator and a Monte-Carlo style exploration policy that prioritizes high-value path expansions. Empirical results on standard KGQA benchmarks show that NeuroSymActive attains strong answer accuracy while reducing the number of expensive graph lookups and model calls compared to common retrieval-augmented baselines.

Figures (10)

• Figure 1: Architectural overview of the NeuroSymActive framework for knowledge graph question answering. The framework operates via a coupled dual-loop optimization process across three main stages: Stage 1: Uncertainty-Aware Active Retrieval, which utilizes a Bayesian head to model heteroscedastic uncertainty in hop prediction and a neural entropy predictor $\eta_\theta$ to estimate information gain ($IG$). This stage selectively invokes a Human Oracle via the $\mathrm{QUERY\_HUMAN}$ action when uncertainty $\mathcal{U}(\mathbf{s}_t)$ exceeds the threshold $\tau_{\mathrm{hop}}$. Stage 2: Differentiable Neural-Symbolic Fusion, where a hybrid Knowledge Adapter merges continuous path embeddings ($\mathbf{z}_f^{\mathrm{neural}}$) with soft symbolic plausibility scores ($\mathbf{z}_f^{\mathrm{sym}}$) derived from a Differentiable Inductive Logic Layer (DILL). Rule confidences $w_\rho$ are updated via gradient signals from active supervision stored in the human replay buffer $\mathcal{D}_{\mathrm{human}}$. Stage 3: Differentiable MCTS with Active Exploration, which implements a relaxed Monte Carlo Tree Search. It employs Progressive Widening governed by predictive uncertainty and treats human intervention as explicit nodes with value $V_{\mathrm{human}}(s)$. The search is fully differentiable via Gumbel-Softmax relaxations, allowing end-to-end joint training of the policy $\pi_\phi$, value $v_\psi$, and symbolic weights through a composite multi-objective loss $\mathcal{L}_{\mathrm{total}}$.
• Figure 2: Reduction in error rates for each failure mode as annotation budget increases. Confidence intervals obtained by bootstrapping.
• Figure 3: Composition of residual errors under strong active supervision. Components include KG incompleteness, question ambiguity, and entropy-predictor bias.
• Figure 4: Accuracy versus annotation cost as controlled by uncertainty threshold $\tau_{\mathrm{human}}$. The adaptive strategy is marked.
• Figure 5: Marginal information gain across successive human queries within episodes. Shaded area denotes variance across queries.

Theorems & Definitions (6)

• Theorem A.1: Inner-loop convergence to stationary points
• Lemma A.2: Bayesian head coverage under sub-Gaussian noise
• Proposition A.3: Entropy predictor concentration
• Theorem A.4: Query complexity under minimum per-query gain
• Lemma A.5: Softmax concentration and action-probability gap
• Theorem A.6: Fusion error bound