# Human-in-the-loop Handling of Knowledge Drift

arXiv: https://arxiv.org/abs/2103.14874 · HTML: https://mlsanity.com/paper/2103.14874/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 60 references that are in the map.
- First posted on arXiv 27 Mar 2021.

## Builds on (most cited first, 16 of 16)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Continual Lifelong Learning with Neural Networks: A Review](https://mlsanity.com/paper/1802.07569/) (2018)
- [Learning under Concept Drift: A Review](https://mlsanity.com/paper/2004.05785/) (2020)
- [Semantic Drift Compensation for Class-Incremental Learning](https://mlsanity.com/paper/2004.00440/) (2020)
- [Towards Open World Recognition](https://mlsanity.com/paper/1412.5687/) (2014)
- [Making deep neural networks right for the right scientific reasons by interacting with their explanations](https://mlsanity.com/paper/2001.05371/) (2020)
- [A survey on domain adaptation theory: learning bounds and theoretical guarantees](https://mlsanity.com/paper/2004.11829/) (2020)
- [The Extreme Value Machine](https://mlsanity.com/paper/1506.06112/) (2015)
- [Interpretable Distribution Features with Maximum Testing Power](https://mlsanity.com/paper/1605.06796/) (2016)
- [Characteristic and Universal Tensor Product Kernels](https://mlsanity.com/paper/1708.08157/) (2017)
- [Concept Drift and Anomaly Detection in Graph Streams](https://mlsanity.com/paper/1706.06941/) (2017)
- [Learning in the Wild with Incremental Skeptical Gaussian Processes](https://mlsanity.com/paper/2011.00928/) (2020)
- [Learning from Ontology Streams with Semantic Concept Drift](https://mlsanity.com/paper/1704.07466/) (2017)

## Built on by (most cited first, 4 of 4)

- [AI, Meet Human: Learning Paradigms for Hybrid Decision Making Systems](https://mlsanity.com/paper/2402.06287/) (2024)
- [Lifelong Personal Context Recognition](https://mlsanity.com/paper/2205.10123/) (2022)
- [Streaming and Learning the Personal Context](https://mlsanity.com/paper/2108.08234/) (2021)
- [Spurious Correlations in Concept Drift: Can Explanatory Interaction Help?](https://mlsanity.com/paper/2407.16515/) (2024)

## Abstract (arXiv)

We introduce and study knowledge drift (KD), a complex form of drift that occurs in hierarchical classification. Under KD the vocabulary of concepts, their individual distributions, and the is-a relations between them can all change over time. The main challenge is that, since the ground-truth concept hierarchy is unobserved, it is hard to tell apart different forms of KD. For instance, introducing a new is-a relation between two concepts might be confused with individual changes to those concepts, but it is far from equivalent. Failure to identify the right kind of KD compromises the concept hierarchy used by the classifier, leading to systematic prediction errors. Our key observation is that in many human-in-the-loop applications (like smart personal assistants) the user knows whether and what kind of drift occurred recently. Motivated by this, we introduce TRCKD, a novel approach that combines automated drift detection and adaptation with an interactive stage in which the user is asked to disambiguate between different kinds of KD. In addition, TRCKD implements a simple but effective knowledge-aware adaptation strategy. Our simulations show that often a handful of queries to the user are enough to substantially improve prediction performance on both synthetic and realistic data.