Skip to content
Abelardo Carlos

InteractiveVLDB 2025 Workshops · LS-NSL

Poderoso: embeddings and expert rules, completing knowledge graphs together

Abelardo Carlos Martínez Lorenzo, Alexander Perfilyev, Volker Markl, Martha Clokie, Thomas Sicheritz-Ponten, Zoi Kaoudi · TU Berlin, University of Copenhagen, University of Leicester, IT University of Copenhagen

Knowledge graphs are always incomplete. Embedding models guess missing links from patterns in the data, but fail where data is sparse; experts know rules the data doesn't show. Poderoso lets the two work in a loop, with any embedding model and any reasoner.

MRR for HolE on LUBM (0.09 → 0.27)
3×MRR for HolE on LUBM (0.09 → 0.27)
better MRR than pLogicNet, and 1.5× better than KALE
3.5×better MRR than pLogicNet, and 1.5× better than KALE
KGE model or reasoner can be plugged in
AnyKGE model or reasoner can be plugged in
01

Where data-driven link prediction runs out

Knowledge graph embeddings place entities and relations in a vector space and score whether a missing triple is likely. Rule mining learns logical patterns from the graph. Both only know what the graph already contains, so they work in dense regions and struggle in sparse ones.

Imagine Bob, a bioinformatician working on bacteriophage therapy. He knows facts from the field that his datasets don't contain, for instance that a certain type of phage can burst the bacterial cell. No embedding will learn that from data that doesn't show it.

Earlier hybrids (KALE, pLogicNet) weave rules into one specific embedding model, which makes them hard to adapt and unable to use ontologies or expert rules.

Neural + symbolic

Embeddings

generalise from patterns; weak where the graph is sparse

Rules

encode what experts know; can only deduce from what is there

Loosely coupled, each one feeds the other: embeddings propose plausible links, rules deduce consequences, and the new facts retrain the embeddings.

02

Two engines, one loop

The neural engine trains a KGE model on the graph. Entities that share relations end up close; a relation is a direction in the space.

NEURAL ENGINE · KGEround 1phage1phage2e_coliklebsiellaintegraserepressorendolysindepolymeraseEscherichiaKlebsiellaUTItraining lossCANDIDATE TRIPLESτ = 0.7sampling weight (1 − clustering coeff.) · KGE scoreencodes(phage1, depolymerase)infects(phage1, klebsiella)encodes(phage2, integrase)encodes(phage2, repressor)genus(klebsiella, Escherichia)sampled from sparse regions of the graphSYMBOLIC ENGINE · RULESR1 host(Y) :- infects(X, Y).R2 broad_host_range(X) :- infects(X, Y1), infect…R3 lysogeny(X, Y) :- phage(X), infects(X, Y), en…R4 anti_biofilm(X) :- encodes(X, depolymerase).R5 therapy_candidate_for(X, Y) :- lysogeny(X, Y)…forward chaining · derived facts

facts in the graph

13 → 13

accepted from KGE

–

derived by rules

0

therapy candidates

–

Graph and rules R1–R5 from Figure 3 and Section 3.2; the reasoning is computed live. Embedding positions, sampled candidates and their scores are illustrative: the paper does not list the KGE outputs. Compare “KGE + rules” with “Rules only”: without the two predicted links, no therapy candidate can be derived.

The hard part is asking the embedding model the right questions. A model can only score triples you give it, and the space of possible triples is enormous:

DBPedia20k

20,143 entities · 12 relations · 120,000 triples

4.9 billion

possible triples (N² × R) to score if nothing were sampled

The graph itself holds 2.5e-3% of them.

LUBM-2

53,860 entities · 32 relations · 268,136 triples

92.8 billion

possible triples (N² × R) to score if nothing were sampled

The graph itself holds 2.9e-4% of them.

So the triples generator samples candidates, weighting entities by their clustering coefficient to explore sparse regions, where true links are more likely to be missing.

03

A use case: finding phage therapies

Phages are viruses that infect bacteria, and a promising answer to antimicrobial resistance. Their genomes are diverse and poorly understood, so deciding which lab experiments to run is hard. Link prediction can propose the hypotheses. Here is the paper's small phage graph with its five expert rules, running live. Step through:

Reasoning over the phage knowledge graph Figure 3 and rules R1–R5, executed live
infectsinfectsinfectsencodesencodesencodesencodescausescausesgenusgenusPhageHostDiseaseintegraserepressorendolysindepolymerasephage1phage2e_coliklebsiellaEscherichiaunary_track_infectionKlebsiella
asserted inferred by rules predicted by the KGEbadge inferred property

Expert rules

  • R1 host(Y) :- infects(X, Y).
  • R2 broad_host_range(X) :- infects(X, Y1), infects(X, Y2), genus(Y1), genus(Y2), notEqual(Y1, Y2).
  • R3 lysogeny(X, Y) :- phage(X), infects(X, Y), encodes(X, integrase), encodes(X, repressor).
  • R4 anti_biofilm(X) :- encodes(X, depolymerase).
  • R5 therapy_candidate_for(X, Y) :- lysogeny(X, Y), broad_host_range(X), anti_biofilm(X).

Nothing derived yet

    Asserted facts only. Step through the stages.

    Forward chaining runs in your browser until no rule adds anything new. Genus facts are added so R2 can compare hosts. The two KGE predictions are illustrative: the paper does not list the model's predictions.
    04

    Results

    On a synthetic benchmark (LUBM) and a DBpedia subgraph, both with RDFS entailment rules, Poderoso almost always improves the embedding model it wraps. The best model differs per dataset (DistMult on LUBM, ComplEx on DBPedia20k), which is exactly why being able to plug in any model matters.

    Link prediction accuracy (Table 2) filtered metrics, higher is better
    TransE
    0.28 → 0.24
    ComplEx
    0.24 → 0.32
    DistMult
    0.28 → 0.35
    HolE
    0.09 → 0.27
    Hybrids
    pLogicNet 0.1 · KALE 0.01
    Arrows go from the plain KGE model to the same model inside Poderoso. Axis from 0 to 0.45.

    Reasoning adds little training time: at most about 34% (DistMult on LUBM), and for TransE the inferred triples even make training converge faster. Both KALE and pLogicNet are slower to converge.

    05

    Open challenges

    Scale

    KGE training and reasoning both grow with the graph and the rules; distributed training and reasoning are the way forward.

    Uncertainty

    KGE outputs are probabilistic, but probabilistic reasoners hurt scalability further.

    Orchestration

    Running the two engines naively in sequence can blow up training time.

    Asking the right questions

    Extracting plausible facts from a model without test data is still open; sampling strategies need work.

    Optimisation

    Choosing the model, fact-extraction strategy and reasoner per task calls for an optimiser, like a query optimiser.

    Earlier work

    The idea of loosely coupling knowledge graph embeddings with ontology-based reasoning first appeared in a 2022 preprint with Zoi Kaoudi and Volker Markl. The work was carried out during a master's thesis at TU Berlin.

    See the 2022 preprint →

    Cite

    @inproceedings{martinezlorenzo2025poderoso,
        title = "Modular Neuro-Symbolic Knowledge Graph Completion",
        author = "Martinez Lorenzo, Abelardo Carlos  and
          Perfilyev, Alexander  and
          Markl, Volker  and
          Clokie, Martha  and
          Sicheritz-Ponten, Thomas  and
          Kaoudi, Zoi",
        booktitle = "VLDB 2025 Workshop: New Ideas for Large-Scale Neurosymbolic Learning Systems (LS-NSL)",
        year = "2025",
        url = "https://www.vldb.org/2025/Workshops/VLDB-Workshops-2025/LS-NSL/LS-NSL25_1.pdf"
    }
    All publications

    Graph and rules from Figure 3; accuracy from Table 2.