COcodelion·Jan 24, 2025Submission
Adaptive Classifier: Dynamic Text Classification with Continuous Learning
2 points · Open discussioncodelion
adaptive-classifier
Python2025–2025
codelion / adaptive-classifier
adaptive-classifier
A flexible, adaptive classification system for dynamic text classification
2Distinct people
7Mentions
0Explicit recommenders
577GitHub stars
What to know before exploring
What it is
A flexible, adaptive classification system for dynamic text classification
GitHub
Where it is used
No documented product use has been verified yet.
What people are saying
No recommendation phrase was found in the indexed comments.
No classified warning is attached to this page. Read the discussions before treating silence as approval.
Also in these discussions
No other repository is repeatedly linked in the same discussions.
This week on Hacker News
Nov 7–Nov 14 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/14/2026, 8:59:20 PM UTC.
No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.
Mentions over time
HN mentions by week7 dated mentions
Observed mentions: 2025-01-21 23:54:32 UTC to 2025-03-07 11:56:47 UTC. Weeks start Monday, UTC.
Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.
View mention counts and date ranges
| Period | Start (UTC) | End (exclusive, UTC) | Mentions | Submissions | Comments |
|---|---|---|---|---|---|
| Jan 20 | 2025-01-20 00:00:00 UTC | 2025-01-27 00:00:00 UTC | 2 | 2 | 0 |
| Jan 27 | 2025-01-27 00:00:00 UTC | 2025-02-03 00:00:00 UTC | 2 | 2 | 0 |
| Feb 3 | 2025-02-03 00:00:00 UTC | 2025-02-10 00:00:00 UTC | 1 | 1 | 0 |
| Feb 10 | 2025-02-10 00:00:00 UTC | 2025-02-17 00:00:00 UTC | 0 | 0 | 0 |
| Feb 17 | 2025-02-17 00:00:00 UTC | 2025-02-24 00:00:00 UTC | 0 | 0 | 0 |
| Feb 24 | 2025-02-24 00:00:00 UTC | 2025-03-03 00:00:00 UTC | 0 | 0 | 0 |
| Mar 3 | 2025-03-03 00:00:00 UTC | 2025-03-10 00:00:00 UTC | 2 | 1 | 1 |
What Hacker News says
2 sourcesShow HN: Adaptive-classifier – text classification with continuous learning
Hi HN! I've built a Python library that lets you create text classifiers that can continuously learn and adapt to new classes without retraining from scratch.
What makes this different from typical text classifiers:
- Dynamically add new classes at any time without full retraining
- Combines neural networks with prototype learning for better few-shot performance
- Uses Elastic Weight Consolidation to prevent catastrophic forgetting
- Works with any HuggingFace transformer base model
- Memory-efficient through prototype-based storage
You can try it out in under a minute:
pip install adaptive-classifier
from adaptive_classifier import AdaptiveClassifier
# Initialize with any HuggingFace model
classifier = AdaptiveClassifier("bert-base-uncased")
# Add initial examples
texts = ["Great product!", "Terrible experience", "Average performance"]
l
Read the rest
abels = ["positive", "negative", "neutral"]
classifier.add_examples(texts, labels)
# Make predictions
print(classifier.predict("This is amazing!"))
# [('positive', 0.85), ('neutral', 0.10), ('negative', 0.05)]
# Add a completely new class later
classifier.add_examples(
["Error 404", "System crashed"],
["technical", "technical"]
)
The library came out of my work on building a model router for optillm where approaches and model types keep changing. Traditional classifiers require full retraining when adding new classes, which becomes impractical with large datasets.
Source code: https://github.com/codelion/adaptive-classifier
I'd love to hear your thoughts and feedback! Happy to answer any questions about the implementation details, use cases, or future plans.