Hakken: Predicting future discoveries to fill the gaps in today's knowledge

• URL: http://arxiv.org/abs/2609.04494v1
• Date: Thu, 03 Sep 2026 21:28:36 GMT
• Title: Hakken: Predicting future discoveries to fill the gaps in today's knowledge
• Abstract summary: We present Hakken, a domain-agnostic prediction and explanation system performing knowledge prediction.<n>Hakken uses a transformer-based prediction model built on temporal sequences of knowledge graphs extracted from vast bodies of research publications.<n>We demonstrate Hakken's practical capabilities by applying it to the biomedical domain.
• Score: 40.777614666509685
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present Hakken, a domain-agnostic prediction and explanation system performing knowledge prediction, i.e., growing scientific knowledge by establishing novel relationships, ones that are not limited to the deductive hull of previous knowledge. Hakken uses a transformer-based prediction model built on temporal sequences of knowledge graphs extracted from vast bodies of research publications, fused with an LLM's semantic knowledge, to predict the presence and define the type of as-yet undocumented relationships between scientific concepts. It then calls a model-agnostic explanation framework to provide accompanying information for each prediction that allows scientists to evaluate the suggested new relationship. While general purpose, we demonstrate Hakken's practical capabilities by applying it to the biomedical domain. There, Hakken's prediction model establishes a new benchmark for time-aware multi-label relation prediction, and we show that the model's output stays coherent and informative over extended time spans in historic data. In addition, we scored 1.5 million above-confidence-threshold hypotheses related to aging, qualitatively validated batches of these predictions with biologists and progressed three of them for empirical validation in wet-lab. Two predictions with potentially significant impact in the context of drug discovery and repurposing were confirmed, introducing previously undocumented interactions between TP53 and BAMBI, and between RAF1 and TNF, to biomedical science.

Related papers

• Rewarding Explainability in Drug Repurposing with Knowledge Graphs [0.9176056742068814]
  This paper presents a novel approach REx, for generating explanations based in link graphs.<n>It employs reward and policy mechanisms that consider desirable properties of scientific explanation.<n>We evaluate our approach in drug repurposing using three popular knowledge graphs.
  arXiv  Detail & Related papers  (2025-09-02T12:55:35Z)
• KEPLA: A Knowledge-Enhanced Deep Learning Framework for Accurate Protein-Ligand Binding Affinity Prediction [60.23701115249195]
  KEPLA is a novel deep learning framework that integrates prior knowledge from Gene Ontology and ligand properties to enhance prediction performance.<n> Experiments on two benchmark datasets demonstrate that KEPLA consistently outperforms state-of-the-art baselines.
  arXiv  Detail & Related papers  (2025-06-16T08:02:42Z)
• Bayesian Kolmogorov Arnold Networks (Bayesian_KANs): A Probabilistic Approach to Enhance Accuracy and Interpretability [1.90365714903665]
  This study presents a novel framework called Bayesian Kolmogorov Arnold Networks (BKANs) BKANs combines the expressive capacity of Kolmogorov Arnold Networks with Bayesian inference. Our method provides useful insights into prediction confidence and decision boundaries and outperforms traditional deep learning models in terms of prediction accuracy.
  arXiv  Detail & Related papers  (2024-08-05T10:38:34Z)
• Graph Stochastic Neural Process for Inductive Few-shot Knowledge Graph Completion [63.68647582680998]
  We focus on a task called inductive few-shot knowledge graph completion (I-FKGC) Inspired by the idea of inductive reasoning, we cast I-FKGC as an inductive reasoning problem. We present a neural process-based hypothesis extractor that models the joint distribution of hypothesis, from which we can sample a hypothesis for predictions. In the second module, based on the hypothesis, we propose a graph attention-based predictor to test if the triple in the query set aligns with the extracted hypothesis.
  arXiv  Detail & Related papers  (2024-08-03T13:37:40Z)
• Selective Temporal Knowledge Graph Reasoning [70.11788354442218]
  Temporal Knowledge Graph (TKG) aims to predict future facts based on given historical ones. Existing TKG reasoning models are unable to abstain from predictions they are uncertain. We propose an abstention mechanism for TKG reasoning, which helps the existing models make selective, instead of indiscriminate, predictions.
  arXiv  Detail & Related papers  (2024-04-02T06:56:21Z)
• Seeing Unseen: Discover Novel Biomedical Concepts via Geometry-Constrained Probabilistic Modeling [53.7117640028211]
  We present a geometry-constrained probabilistic modeling treatment to resolve the identified issues. We incorporate a suite of critical geometric properties to impose proper constraints on the layout of constructed embedding space. A spectral graph-theoretic method is devised to estimate the number of potential novel classes.
  arXiv  Detail & Related papers  (2024-03-02T00:56:05Z)
• Otter-Knowledge: benchmarks of multimodal knowledge graph representation learning from different sources for drug discovery [5.913390277336069]
  We release a set of multimodal knowledge graphs, integrating data from seven public data sources, and containing over 30 million triples. Our intention is to foster additional research to explore how multimodal knowledge enhanced protein/molecule embeddings can improve prediction tasks.
  arXiv  Detail & Related papers  (2023-06-22T11:01:41Z)
• Temporal Positive-unlabeled Learning for Biomedical Hypothesis Generation via Risk Estimation [46.852387038668695]
  This paper aims to introduce the use of machine learning to the scientific process of hypothesis generation. We propose a variational inference model to estimate the positive prior, and incorporate it in the learning of node pair embeddings. Experiment results on real-world biomedical term relationship datasets and case study analyses on a COVID-19 dataset validate the effectiveness of the proposed model.
  arXiv  Detail & Related papers  (2020-10-05T10:58:03Z)
• Rationalizing Medical Relation Prediction from Corpus-level Statistics [27.5727760575915]
  We present a new interpretable framework inspired by existing theories on how human memory works, e.g., theories of recall and recognition. We conduct experiments on a real-world public clinical dataset and show that our framework can not only achieve competitive predictive performance against a comprehensive list of neural baseline models, but also present rationales to justify its prediction.
  arXiv  Detail & Related papers  (2020-05-02T17:39:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.