# Adapting Neural Link Predictors for Data-Efficient Complex Query Answering

arXiv: https://arxiv.org/abs/2301.12313 · HTML: https://mlsanity.com/paper/2301.12313/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 47 references that are in the map.
- First posted on arXiv 29 Jan 2023.

## Builds on (most cited first, 26 of 26)

- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Modeling Relational Data with Graph Convolutional Networks](https://mlsanity.com/paper/1703.06103/) (2017)
- [Embedding Entities and Relations for Learning and Inference in Knowledge Bases](https://mlsanity.com/paper/1412.6575/) (2014)
- [Complex Embeddings for Simple Link Prediction](https://mlsanity.com/paper/1606.06357/) (2016)
- [RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space](https://mlsanity.com/paper/1902.10197/) (2019)
- [Convolutional 2D Knowledge Graph Embeddings](https://mlsanity.com/paper/1707.01476/) (2017)
- [An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks](https://mlsanity.com/paper/1312.6211/) (2013)
- [Composition-based Multi-Relational Graph Convolutional Networks](https://mlsanity.com/paper/1911.03082/) (2019)
- [TuckER: Tensor Factorization for Knowledge Graph Completion](https://mlsanity.com/paper/1901.09590/) (2019)
- [Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction](https://mlsanity.com/paper/2106.06935/) (2021)
- [DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning](https://mlsanity.com/paper/1707.06690/) (2017)
- [A Review of Relational Machine Learning for Knowledge Graphs](https://mlsanity.com/paper/1503.00759/) (2015)
- [Inductive Relation Prediction by Subgraph Reasoning](https://mlsanity.com/paper/1911.06962/) (2019)
- [DRUM: End-To-End Differentiable Rule Mining On Knowledge Graphs](https://mlsanity.com/paper/1911.00055/) (2019)
- [Query2box: Reasoning over Knowledge Graphs in Vector Space using Box Embeddings](https://mlsanity.com/paper/2002.05969/) (2020)
- [Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning](https://mlsanity.com/paper/1711.05851/) (2017)
- [Canonical Tensor Decomposition for Knowledge Base Completion](https://mlsanity.com/paper/1806.07297/) (2018)
- [Beta Embeddings for Multi-Hop Logical Reasoning in Knowledge Graphs](https://mlsanity.com/paper/2010.11465/) (2020)
- [Embedding Logical Queries on Knowledge Graphs](https://mlsanity.com/paper/1806.01445/) (2018)
- [Complex Query Answering with Neural Link Predictors](https://mlsanity.com/paper/2011.03459/) (2020)
- [ConE: Cone Embeddings for Multi-Hop Reasoning over Knowledge Graphs](https://mlsanity.com/paper/2110.13715/) (2021)
- [Neural-Symbolic Models for Logical Queries on Knowledge Graphs](https://mlsanity.com/paper/2205.10128/) (2022)
- [Self-Supervised Hyperboloid Representations from Logical Queries over Knowledge Graphs](https://mlsanity.com/paper/2012.13023/) (2020)
- [Probability Calibration for Knowledge Graph Embedding Models](https://mlsanity.com/paper/1912.10000/) (2019)
- [LowFER: Low-rank Bilinear Pooling for Link Prediction](https://mlsanity.com/paper/2008.10858/) (2020)
- [Reasoning on Knowledge Graphs with Debate Dynamics](https://mlsanity.com/paper/2001.00461/) (2020)

## Built on by (most cited first, 13 of 13)

- [Neurosymbolic AI for Reasoning over Knowledge Graphs: A Survey](https://mlsanity.com/paper/2302.07200/) (2023)
- [A Foundation Model for Zero-shot Logical Query Reasoning](https://mlsanity.com/paper/2404.07198/) (2024)
- [Is Complex Query Answering Really Complex?](https://mlsanity.com/paper/2410.12537/) (2024)
- [Conditional Logical Message Passing Transformer for Complex Query Answering](https://mlsanity.com/paper/2402.12954/) (2024)
- [A Neuro-Symbolic Framework for Answering Graph Pattern Queries in Knowledge Graphs](https://mlsanity.com/paper/2310.04598/) (2023)
- [Pathformer: Recursive Path Query Encoding for Complex Logical Query Answering](https://mlsanity.com/paper/2406.14880/) (2024)
- [Complex Logical Query Answering by Calibrating Knowledge Graph Completion Models](https://mlsanity.com/paper/2410.07165/) (2024)
- [On the Theoretical Limitations of Embedding-based Link Prediction](https://mlsanity.com/paper/2506.22271/) (2025)
- [Interactive Query Answering on Knowledge Graphs with Soft Entity Constraints](https://mlsanity.com/paper/2508.13663/) (2025)
- [CQD-SHAP: Explainable Complex Query Answering via Shapley Values](https://mlsanity.com/paper/2510.15623/) (2025)
- [Counting Still Counts: Understanding Neural Complex Query Answering Through Query Relaxation](https://mlsanity.com/paper/2511.22565/) (2025)
- [A Survey on GNN-based Link Prediction: Techniques, Applications, and Challenges](https://mlsanity.com/paper/2607.16198/) (2026)
- [SCAIR: Schema-Conditioned Agentic Iterative Reasoning for Enterprise Knowledge Graphs](https://mlsanity.com/paper/2607.22571/) (2026)

## Abstract (arXiv)

Answering complex queries on incomplete knowledge graphs is a challenging task where a model needs to answer complex logical queries in the presence of missing knowledge. Prior work in the literature has proposed to address this problem by designing architectures trained end-to-end for the complex query answering task with a reasoning process that is hard to interpret while requiring data and resource-intensive training. Other lines of research have proposed re-using simple neural link predictors to answer complex queries, reducing the amount of training data by orders of magnitude while providing interpretable answers. The neural link predictor used in such approaches is not explicitly optimised for the complex query answering task, implying that its scores are not calibrated to interact together. We propose to address these problems via CQDA, a parameter-efficient score adaptation model optimised to re-calibrate neural link prediction scores for the complex query answering task. While the neural link predictor is frozen, the adaptation component -- which only increases the number of model parameters by 0.03% -- is trained on the downstream complex query answering task. Furthermore, the calibration component enables us to support reasoning over queries that include atomic negations, which was previously impossible with link predictors. In our experiments, CQDA produces significantly more accurate results than current state-of-the-art methods, improving from 34.4 to 35.1 Mean Reciprocal Rank values averaged across all datasets and query types while using ≤ 30% of the available training query types. We further show that CQDA is data-efficient, achieving competitive results with only 1% of the training complex queries, and robust in out-of-domain evaluations.