Three Tricks to Amplify Small Data for Deep Learning
It’s no secret that deep learning lets data science practitioners reach new levels of accuracy with predictive models. However, one of the drawbacks of deep learning is it typically requires huge data sets (not to mention big clusters). But with a little skill, practitioners with smaller data sets can still partake of deep learning riches.
Deep learning has exploded in popularity, with good reason: Deep learning approaches, such as convolutional neural networks (used primarily for image data) and recurrent neural networks (used primarily for language and textual data) can deliver higher accuracy and precision compared to “classical” machine learning approaches, like regression algorithms, gradient-boosted trees, and support vector machines.
But that higher accuracy comes at a cost. Deep learning models are much more complex and typically require much more data to deliver better predictions. And of course, running all that data requires more computer horsepower, typically in the form of GPU-equipped clusters. It’s no wonder that the world’s leaning practitioners of deep learning are companies with names like Google, Facebook, and Microsoft, which have a ton of data and compute capacity on which to develop and train advanced predictive models.
Size does matter, but that doesn’t leave mere data mortals out in the cold. With the right techniques, data scientists and machine learning engineers can get in on the deep learning action, but without a huge corpus of training data up front.
One of the technologists with a lot of experience making the most of smaller data is Vaibhav Nivargi, the CTO and co-founder of Moveworks, which develops IT ticket automation software. The company is just three-and-a-half years old and is backed by some of the top venture capitalists in Silicon Valley. But it doesn’t have a ton of IT tickets on which to train its predictive models, which posed a challenge to Nivargi.
“IT tickets are not really the most voluminous types of data,” Nivargi says. “Even if you have a customer with several thousand employees, it’s a relatively infrequent activity to file an IT ticket. The data sets are relatively sparse and small. To be able to leverage more sophisticated techniques, running at very high levels of accuracy and precision, is highly non-trivial.”
Under Nivargi’s watch, Moveworks has swung above its weight and developed deep learning models that are much more accurate and precise compared to traditional machine learning approaches. These three techniques detail how he did it.
Transfer learning is arguably the most basic approach to leveraging powerful deep learning approaches when you don’t have the data to develop a more custom solution. At its most basic level, it’s a copy and paste approach: You copy a deep learning model that’s already been developed, but paste your custom code into the last layer that develops the final prediction.
Moveworks adopted BERT, a recurrent network model developed and open sourced by Google for natural language understanding, as the basis for one of the deep learning models it uses to understand the words that its customers use as they interact with an IT help desk.
“Think of transfer learning as fine tuning,” Nivargi tells Datanami. “You already have something that’s reasonably working, but you want to make it work for your use case. You take most of what it has learned, and you just change the last few steps.”
Collective learning is a technique that can be used to amplify your existing sparse data to generate new data that’s very close to the distribution of real world data. More data, of course, equals better results in a deep learning model.
Using collective learning techniques to boost the available corpus of training data in the computer vision domain is fairly straightforward. “You can take the image and tweak the contrast,” Nivargi says. “Or you can rotate the image or chop off the sides, and now you have 3x to 4x that data.”
It’s trickier to do in the language domain, because you can’t just chop off the end of words or add random words and punctuation. But with enough care in the hands of a knowledgeable practitioner, the collective learning approach can also be used to boost an existing data set and provide more collections of words to feed into the recurrent neural network.
“We have language like ‘I’m trying to set up a meeting with X’ or ‘I’m getting error Y. Can you help me?’” Nivargi says. “You can substitute a meeting with Zoom or WebEx or GoToMeeting, and mix and match the preamble and the problem, and still get data that is very realistic.”
Meta learning, which is sometimes called n-shot or multi-shot learning, is another powerful data-boosting technique. According to Nivargi, Moveworks uses meta learning to create additional dimensions of the data, which allows the deep learning models to better understand the shape of the data.
Let’s say I see an IT ticket that says ‘I need access to the dashboard so I can publish a metric,’” Nivargi says. “It’s perfectly valid, syntactical English. It’s meaningful. But it’s completely incomplete. We don’t know what kind of dashboard.”
To fill in the blanks and drive toward a greater understanding of what that employee meant, Moveworks employs a meta learning approach that applies context to the statement. The approach uses available metadata to make a guess about what the employee meant.
“You can use an example of what department the employee works in, or the time of day,” Nivargi says. “If the employee in in marketing, there’s a good chance they’re talking about the Salesforce dashboard. If they’re in engineering, there’s a good chance they’re talking about the Jira dashboard.”
DL for the Masses
Collectively, these three techniques let Moveworks specifically amplify this data to a very high volume, Nivargi says.
Transfer learning has a bootstrap phenomenon, where you can start from a strong base and then adapt to your domain,” he says. “Collective learning has a network effective. And meta learning can take data from N dimensions and add several hundred dimensions more. So all of these are cumulatively very, very powerful.”
Moveworks employs a wide variety of supervised and unsupervised machine learning and deep learning models to help understand the meaning of IT help desk tickets. Some models are universal and some are customer-specific and some are ensembles. Like most companies active in data science, it’s found some techniques work well in some domains, while other approaches require completely different approaches.
In the early days of the company, Moveworks hit a wall with traditional machine learning models. One of them was “saturated” at around 82% accuracy. “It would simply not learn above that,” Nivargi says. “The model would plateau.”
After employing some of the transfer learning, collective learning, and meta learning tricks discussed here, Moveworks had enough data to keep the bigger deep learning models flush with data. As a result, the models are more accurate.
“Some of our models now can be deployed in production in the high 90s, 90% to 96% precision, and we can have very high coverage as well,” he says. “So now we can use extremely powerful and sophisticated deep learning techniques without requiring the same kind of inherent data that a Google or Facebook or Microsoft has.”
September 27, 2022
- Storebrand Deploys Bloomberg’s BQuant Enterprise
- Wasabi Technologies Closes $250M in New Funding for Cloud Storage
September 26, 2022
- Qlik Expands Strategic Alignment with Databricks Through SQL-Based Ingestion
- AppTek and expert.ai Announce Strategic Partnership
September 23, 2022
- Fluree and ZettaLabs Announce Merger to Serve Enterprise Data Infrastructure Modernization
- AI Skills Crisis May Lead to Wasted Investments and Stifled Innovation: SAS
September 22, 2022
- Quest Software Announces Public Beta for SharePlex for PostgreSQL
- Netskope Chooses YugabyteDB to Scale SASE Capabilities
- Alation and Fivetran Announce Strategic Partnership for the Modern Data Stack
- Cohere For AI Announces ML Scholars Program
- Kyndryl and Elastic Announce Expanded Partnership
- Dataminr Announces Availability of Dataminr Pulse in AWS Marketplace and Joins AWS ISV Accelerate Program
- Spectra Logic and iRODS Consortium Partner to Provide Glacier-Like Tier of Storage
- BigID Announces Native Data Security Controls for Snowflake
- MinIO Surpasses 1 Billion Cumulative Docker Downloads
- IntelliProp Unveils Its Omega Memory Fabric Chips
- SES, ESA and European Commission Partnering to Deliver Satellite Quantum Cryptography System
- Falkonry Unveils GPU-Based, High-Speed Time Series Anomaly Detection Application
September 21, 2022
- Coforge and Databricks Announce Partnership
- New Study Develops a Lossless Data Management Platform for ML and Sharing Experimental Information
Most Read Features
- Data Mesh Vs. Data Fabric: Understanding the Differences
- Walmart Gives Data and Analytics Monetization A Try
- Teradata Unveils New Data Lake, Advanced Analytics Offerings
- Big Data File Formats Demystified
- How Providence Overcame Security Obstacles to Unlock Medical Data in the Cloud
- Five Common AI/ML Project Mistakes
- How the Coronavirus Response Is Aided by Analytics
- Who’s Winning In the $17B AIOps and Observability Market
- Cloud Migrations Negatively Impacting Data Estates, Capital One Says
- Five Real-World Applications for Sports Analytics
- More Features…
Most Read News In Brief
- Mathematica Helps Crack Zodiac Killer’s Code
- MIT and Databricks Report Finds Data Management Key to Scaling AI
- Big Growth Forecasted for Big Data
- LinkedIn Donates Feature Store to Linux Foundation
- New C++ Acceleration Library Velox Juices Code Execution Up To 8x
- Nvidia Could Become Google of the Metaverse with AI Search Engine
- Big Data Career Notes: September 2022 Edition
- Pecan AI Leaps Over the Skills Gap to Enable Data Science On Demand
- Data Prep Still Dominates Data Scientists’ Time, Survey Finds
- These 15 Data Fabrics Made the Cut in Forrester’s Wave
- More News In Brief…
Most Read This Just In
- Salesforce and AWS Announce Expansion of Strategic Partnership
- SingleStore Selects AppDirect to Power Real-Time Marketplace
- Zendesk Launches New Customer Sentiment and Intent Functionality Powered by ML
- Nvidia and Dell Technologies Announce New Data Center Solution
- Dell Technologies Establishes Partnership with Deep North
- Starburst Highlights Q2 Company and Customer Growth
- TDengine Releases TDengine Cloud
- Netskope Chooses YugabyteDB to Scale SASE Capabilities
- Gartner Recognizes Fivetran for Highest Growth in Data Integration Sector
- Intel Announces Availability of 12th Gen Intel Core SoC Processors for IoT Edge
- More This Just In…
Sponsored Partner Content
October 5 - October 6Santa Clara CA United States
October 10 - October 12Boston MA United States
October 17 - October 20Toronto ON Canada
October 20 - October 21Boston MA United States
November 9 - November 10Washington DC United States