newsrex/NAML-JAX-MIND-small-bert-random

NewsReX NAML — JAX — MIND-small

NAML news recommendation model trained on MIND-small using the NewsReX framework (JAX).

Test Results

Seed	AUC	MRR	NDCG@5	NDCG@10
123 *	0.6690	0.3148	0.3472	0.4123
42	0.6659	0.3148	0.3493	0.4133
456	0.6632	0.3151	0.3471	0.4101
mean ± std	0.6661±0.0024	0.3149±0.0001	0.3478±0.0010	0.4119±0.0013

* Best seed (weights at repo root)

Experiment Configuration

model:
  name: naml
  architecture:
    news_encoder:
      type: cnn_multi_view
      views:
        title:
          type: cnn
          filter_num: 400
          kernel_size: 3
          activation: relu
          attention_query_dim: 200
        abstract:
          type: cnn
          filter_num: 400
          kernel_size: 3
          activation: relu
          attention_query_dim: 200
        category:
          type: embedding
          embedding_dim: 100
        subcategory:
          type: embedding
          embedding_dim: 100
      view_attention_query_dim: 200
    user_encoder:
      type: additive_attention
      attention_query_dim: 200
      num_attention_heads: 10
    click_predictor:
      type: dot_product
  embedding:
    size: 300
    trainable: true
  dropout_rate: 0.2
  seed: 42
inputs:
  title:
    max_length: 32
  abstract:
    max_length: 50
  history:
    max_length: 50
  impressions:
    max_length: 5
  process_title: true
  process_abstract: true
  process_category: true
  process_subcategory: true
  process_user_id: false
training:
  loss:
    name: categorical_crossentropy
    from_logits: true
    reduction: sum_over_batch_size
    label_smoothing: 0.0
  optimizer: adam
  learning_rate: 0.0001
  batch_size: 256
  num_epochs: 10
  early_stopping:
    patience: 3
    min_improvement: 0.01
  negative_sampling:
    strategy: random
    candidates: 4
evaluation:
  mode: fast
  metrics:
  - auc
  - mrr
  - ndcg@5
  - ndcg@10
  batch_size: 512

Repository Structure

newsrex/NAML-JAX-MIND-small-bert-random/
├── model.safetensors          ← best seed (123)
├── test_results.json
├── training_run_summary.json
├── seed_123/model.safetensors
├── seed_42/model.safetensors
├── seed_456/model.safetensors
└── README.md

Usage

git clone https://github.com/igor17400/NewsReX.git
cd NewsReX && uv sync

# Run evaluation with best seed weights
uv run python src/eval.py \
    experiment=mind/glove/naml \
    framework=jax \
    weights=hf://newsrex/NAML-JAX-MIND-small-bert-random/model.safetensors

# Run evaluation with a specific seed
uv run python src/eval.py \
    experiment=mind/glove/naml \
    framework=jax \
    weights=hf://newsrex/NAML-JAX-MIND-small-bert-random/seed_42/model.safetensors

Citation

@misc{newsrex2026,
  title={NewsReX: An Open-Source Multi-Framework for Neural News Recommendation},
  author={Igor L. R. Azevedo and Toyotaro Suzumura and Yuichiro Yasui},
  year={2025},
  eprint={2508.21572},
  archivePrefix={arXiv},
  primaryClass={cs.IR},
  url={https://arxiv.org/abs/2508.21572},
}