Jul 31, 2018 · newsletter

Progress in machine learning interpretability

Our goal when we do research is to address capabilities and technologies that we expect to become production-ready in one to two years. That focus on fast-moving areas means that new algorithmic ideas sometimes come along that allow our clients to extend or improve upon the work in our reports.

We published our report on machine learning interpretability last year. The technical focus of our report was LIME, a tool that computes locally correct explanations of a model’s behaviour. If a model is good, LIME’s explanations can offer completely new insights. (We saw this in our prototype, which models customer churn using traditional machine learning techniques, but then uses LIME to say precisely what it is about a customer that makes them a churn risk.) And if a model is bad, LIME can help you understand why.

This all sounds great, but we had to leave three issues unresolved in our report. Progress since last year has begun to address those concerns.

LIME explanations of sentiment classification. “Not” is a positive word in one example, but not in another. Image credit: Anchors.

Firstly, LIME’s explanations are local. For example, a LIME explanation may (correctly) tell you that “This movie is not bad” has positive sentiment because it contains the word “not.” But because LIME’s explanations are local, a user is not generally entitled to conclude from this that the word “not” always indicates positive sentiment. This makes sense: the presence of “not” in “this movie is not very good” does not tell you its sentiment is positive! But how local is “local”? How similar to the original sentence does a new sentence need to be for LIME’s explanation to apply?

Anchors explanations of sentiment classification. “Not” is a positive word in combination with “bad.” Image credit: Anchors.

The creators of LIME offer an answer to this question in the form of Anchors: High-Precision Model-Agnostic Explanations(PDF, 2.7MB).” Anchors works like LIME in that it probes the behaviour of the black-box model by perturbing the original example. But it takes a very different approach to constructing a human-friendly explanation. Rather than fit a locally correct linear model (which raises the question: how local?), it constructs a set of rules. For the “this movie is not bad” example above, the rule might be “sentence contains ‘not’ and ‘bad’". Such black and white rules are easier for many people to understand than quantitative weights. And they implicitly define locality: if the sentence doesn’t contain “not” or “bad,” the rule (and the explanation) doesn’t apply. The Anchors code is publicly available.

SHAP explanation of a prediction for a model of the Boston house price dataset.

Secondly, LIME’s choice of perturbation strategy and its local linear model are heuristics – which is to say they feel a little arbitrary, and it’s reasonable to wonder whether they are optimal in practice. In A Unified Approach to Interpreting Model Predictions Lundberg and Lee carefully define what we mean by optimal, and show that LIME is a specific example of a more general class of explanation tools they call “additive feature attribution methods.” This class includes the classical “Shapley” feature importance measure familiar to economists, and DeepLIFT, a neural network interpretability tool. They unify this class in a provably optimal way they call SHAP. The code is public, and is highly optimized for the particular case of tree-based methods such as XGboost. One thing we really like about SHAP is that the built-in visualization tools are very nice! This seemingly minor point is surprisingly important to the adoption of new tools, and we’re glad to see these authors spend time on this aspect of their code.

Finally, how do we test explanations? How do we know whether an explanation is evidence of a problem with the model or a surprising insight? Patrick Hall and colleagues at sum up the current situation very well in a new article for O’Reilly Testing machine learning interpretability techniques. The conclusion is: “use more than one type of tool to explain your machine learning models, and look for consistent results across different explanatory methods.” We agree, and we’re glad to see new options such as Anchors and SHAP that make this easy!

So, a year after our report, machine learning interpretability remains not only a very useful business capability, but a vibrant area of research.

Read more

Aug 15, 2018 · scifi
Jul 31, 2018 · newsletter

Latest posts

Dec 14, 2021 · post

An Introduction to Video Understanding: Capabilities and Applications

by Daniel Valdez Balderas · Video footage constitutes a significant portion of all data in the world. The 30 thousand hours of video uploaded to Youtube every hour is a part of that data; another portion is produced by 770 million surveillance cameras globally. In addition to being plentiful, video data has tremendous capacity to store useful information. Its vastness, richness, and applicability make the understanding of video a key activity within the field of computer vision. more
Sep 22, 2021 · post

Automatic Summarization from TextRank to Transformers

by Melanie Beck · Automatic summarization is a task in which a machine distills a large amount of data into a subset (the summary) that retains the most relevant and important information from the whole. While traditionally applied to text, automatic summarization can include other formats such as images or audio. In this article we’ll cover the main approaches to automatic text summarization, talk about what makes for a good summary, and introduce Summarize. – a summarization prototype we built that showcases several automatic summarization techniques. more
Sep 21, 2021 · post

Extractive Summarization with Sentence-BERT

by Victor Dibia · In extractive summarization, the task is to identify a subset of text (e.g., sentences) from a document that can then be assembled into a summary. Overall, we can treat extractive summarization as a recommendation problem. That is, given a query, recommend a set of sentences that are relevant. The query here is the document, relevance is a measure of whether a given sentence belongs in the document summary. How we go about obtaining this measure of relevance varies (a common dilemma for any recommendation system). more
Sep 20, 2021 · post

How (and when) to enable early stopping for Gensim's Word2Vec

by Melanie Beck · The Gensim library is a staple of the NLP stack. While it primarily focuses on topic modeling and similarity for documents, it also supports several word embedding algorithms, including what is likely the best-known implementation of Word2Vec. Word embedding models like Word2Vec use unlabeled data to learn vector representations for each token in a corpus. These embeddings can then be used as features in myriad downstream tasks such as classification, clustering, or recommendation systems. more
Jul 7, 2021 · post

Exploring Multi-Objective Hyperparameter Optimization

By Chris and Melanie. The machine learning life cycle is more than data + model = API. We know there is a wealth of subtlety and finesse involved in data cleaning and feature engineering. In the same vein, there is more to model-building than feeding data in and reading off a prediction. ML model building requires thoughtfulness both in terms of which metric to optimize for a given problem, and how best to optimize your model for that metric! more
Jun 9, 2021 ·

Deep Metric Learning for Signature Verification

By Victor and Andrew. TLDR; This post provides an overview of metric learning loss functions (constrastive, triplet, quadruplet, and group loss), and results from applying contrastive and triplet loss to the task of signature verification. A complete list of the posts in this series is outlined below: Pretrained Models as Baselines for Signature Verification -- Part 1: Deep Learning for Automatic Offline Signature Verification: An Introduction Part 2: Pretrained Models as Baselines for Signature Verification Part 3: Deep Metric Learning for Signature Verification In our previous blog post, we discussed how pretrained models can serve as strong baselines for the task of signature verification. more

Popular posts

Oct 30, 2019 · newsletter
Exciting Applications of Graph Neural Networks
Nov 14, 2018 · post
Federated learning: distributed machine learning with data locality and privacy
Apr 10, 2018 · post
PyTorch for Recommenders 101
Oct 4, 2017 · post
First Look: Using Three.js for 2D Data Visualization
Aug 22, 2016 · whitepaper
Under the Hood of the Variational Autoencoder (in Prose and Code)
Feb 24, 2016 · post
"Hello world" in Keras (or, Scikit-learn versus Keras)


In-depth guides to specific machine learning capabilities


Machine learning prototypes and interactive notebooks


A usable library for question answering on large datasets.

Explain BERT for Question Answering Models

Tensorflow 2.0 notebook to explain and visualize a HuggingFace BERT for Question Answering model.

NLP for Question Answering

Ongoing posts and code documenting the process of building a question answering model.

Interpretability Revisited: SHAP and LIME

Explore how to use LIME and SHAP for interpretability.


Cloudera Fast Forward is an applied machine learning reseach group.
Cloudera   Blog   Twitter