Comments (6)
I've updated the description to make it clearer which tasks are in scope for 22.07. I think we can achieve a self-contained operator for Implicit for the upcoming release.
from merlin.
@benfred , please add the tickets related to this epic here
from merlin.
@EvenOldridge @benfred , is Batch prediction in NVTabular section required for 22.04 ?
from merlin.
For the serving part. My understanding is that, for both Implicit and LightFM, the way to serve these at scale is similar to the two tower / bi-encoder design of the DLRM example we have.
Where the item embeddings are stored in a approximate-nearest neighbour search index. And we search through this space using a user embedding. (for user->item recommendations).
The difference from the DLRM example, is in how the user embedding is computed at serving time.
Computing the User Embedding:
- LightFM represents users and items as an aggregation (sum) of their feature embeddings. In this case we would lookup all the feature embeddings corresponding to the user and then aggregate (sum) these.
- Implicit has support for a few different models. Each has the concept of an item and user (factor/embedding)
The alternating least-squares implementation (ALS) appears to be the only one that supports calculating the user factor (embedding) for unseen/new users by running the solver provided items the user has interacted and some model parameters (I'm currently unsure if it would be feasible to store this in practice in a serving scenario / how fast this inference would be).
However, for the case where we have the user factors/embeddings computed already, we can look these up at query-time.
It seems that one of the main questions is where do we store the user/item/feature embeddings for fast lookup at serving time. Ideally with support for versioning (for migrating to new model version) / updating (for new users and items).
For vector/embedding based item->user, user->user, item->item recommendations. two main components are:
- Storing user/item/feature embeddings (Key-value lookup) + optional aggregation (e.g. in the case of LightFM)
- Approximate Nearest Neighbour search through item or user space.
We currently have the QueryFaiss operator. Which is currently limited to a pre-computed index. (so would need to re-compute the index and re-deploy Triton for new items to be considered.) -> Issue for extending functionality of the nearest neighbour candidate retrieval here NVIDIA-Merlin/systems#10
We could start with a similar approach to the nearest neighbour implementation we have now. A first pass at this could be to store the user/feature embeddings as static data inside Triton. Albeit with similar challenges to having the item embeddings index stored as file(s) inside Triton (updating, and scaling to large numbers of items/users). Or they could be managed in a database outside Triton.
from merlin.
@benfred / @oliverholworthy , please fill up the problem, goal and constraints section in the description. You may have provided this in the comments. Please summarise it there. Let me know if you are facing any difficulties.
from merlin.
@oliverholworthy , I have added 22.07 in the description to specify that the task is in scope for 22.07. If it needs to be moved out to future release, please specify
from merlin.
Related Issues (20)
- [BUG] Update Training and Serving Merlin on AWS SageMaker using latest merlin image HOT 5
- [BUG] The multi-stage example is broken due to recent changes in systems HOT 1
- [RMP] Add support for ranking models in PyTorch
- POC on how to build a session-based recommendation pipeline that can deal with the item cold-start problem
- POC on how to build a session-based recommendation model that can be used to re-rank candidate items
- [Task] Centralize API Documentation in Merlin
- [RMP] Update Merlin Models TensorFlow API to Match PyTorch API
- [BUG] User cannot deploy Merlin image >=23.04 on Azure Databricks
- [QST] Where to get tensorflow2.10.1+nv22.12 source code ?
- [QST] How to serve merlin-tensorflow model in Triton Inference Server and convert it to ONNX? HOT 1
- Use MLflow Experiments with Merlin containers[QST] HOT 5
- [BUG] Merlin io - ModuleNotFoundError: No module named 'cudf._version' HOT 2
- [QST]Follow the example 'getting started movies' to execute an error. HOT 3
- [BUG] FileNotFoundError when apply Categorify after JoinExternal HOT 1
- [BUG] CUDA context error HOT 1
- [BUG]Unauthorized with docker build HOT 1
- [QST] Status: CUDA driver version is insufficient for CUDA runtime version HOT 1
- [QST] What is the best way of handling string UUIDs in Merlin? HOT 2
- [QST] Help w/ exporting Retrieval Model. HOT 5
- [QST] What is the best way of handling string UUIDs in Merlin? HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from merlin.