Scalable Structure Learning for Probabilistic Soft Logic
This work addresses scalability issues in structure learning for PSL, which is incremental as it builds on existing relational frameworks to improve efficiency for practitioners in machine learning.
The paper tackles the high computational cost of structure learning in probabilistic soft logic (PSL) by proposing two new methods, including a scalable optimization approach that uses a piecewise pseudolikelihood objective. The results show that this method achieves an order of magnitude runtime speedup and up to 15% AUC gains over greedy search across five real-world tasks.
Statistical relational frameworks such as Markov logic networks and probabilistic soft logic (PSL) encode model structure with weighted first-order logical clauses. Learning these clauses from data is referred to as structure learning. Structure learning alleviates the manual cost of specifying models. However, this benefit comes with high computational costs; structure learning typically requires an expensive search over the space of clauses which involves repeated optimization of clause weights. In this paper, we propose the first two approaches to structure learning for PSL. We introduce a greedy search-based algorithm and a novel optimization method that trade-off scalability and approximations to the structure learning problem in varying ways. The highly scalable optimization method combines data-driven generation of clauses with a piecewise pseudolikelihood (PPLL) objective that learns model structure by optimizing clause weights only once. We compare both methods across five real-world tasks, showing that PPLL achieves an order of magnitude runtime speedup and AUC gains up to 15% over greedy search.