Concept library
1129 concepts across 20 domains and 101 tracks. Each track is a coherent sequence — read it top to bottom or dip in wherever the gap is.
All domains
01Foundations
02Transformer Internals
03Training & Fine-Tuning
04Reinforcement Learning
05Inference, Systems & Hardware
06Applied LLM Engineering
07Reasoning, Evaluation & Safety
08Multimodal & Applications
09Classical ML & Statistical Learning
10Causal Inference & Experimentation
11Time Series & Forecasting
12Graphs, Recommenders & Structured Data
13Generative Modelling Beyond Transformers
14Efficiency, Compression & Edge AI
15Search & Information Retrieval
16Data & Feature Engineering
17MLOps & Platform Engineering
18Security, Privacy & Adversarial ML
19Governance, Risk & Responsible AI
20Human-AI Interaction, Product & Economics
12
Graphs, Recommenders & Structured Data
Learning over relations, catalogues and columns rather than free text.
4tracks
31concepts
358cards
3.9hreading
Graph Neural Networks Message passing, expressive power and the WL test, over-smoothing, over-squashing and sampling at scale. 7 concepts · 74 cards
- 01 Expressive Power and the WL Test The exact ceiling on what a message-passing network can distinguish, why the aggregation function determines whether that ceiling is reached, and the graphs it provably cannot tell apart.
- 02 Graph Attention Networks and Graph Transformers How attention replaces fixed neighbour weights in GAT, why the original GAT can only compute a static ranking of neighbours, and how graph transformers attend globally while injecting structure through positional and structural encodings.
- 03 Heterogeneous and Temporal Graphs Why real graphs have typed nodes and edges that a homogeneous model averages together, how relation-specific message passing preserves the distinction, and what adding time requires.
- 04 Link Prediction and Negative Sampling Why predicting edges is not ordinary classification, how negative sampling choices determine what the model learns, and the evaluation leakage that makes published numbers hard to trust.
- 05 Over-Smoothing and Over-Squashing The two distinct reasons deep graph networks fail, why they pull in opposite directions, and the interventions that address each.
- 06 Sampling and Scaling to Large Graphs Why full-batch training does not scale past a certain graph size, the neighbourhood explosion that makes naive mini-batching worse, and the three sampling strategies that resolve it.
- 07 Spectral Graph Convolutions Defining convolution on a graph through the eigenvectors of its Laplacian, how Chebyshev polynomials make the filter local and cheap, and how the familiar GCN layer falls out as a first-order approximation with a renormalisation trick.
Knowledge Graphs Triples and ontologies, entity resolution, embedding-based link prediction, and grounding LLMs in structure. 6 concepts · 65 cards
- 01 Graph Query Languages: SPARQL, Cypher and GQL How SPARQL matches triple patterns over RDF and Cypher matches ASCII-art patterns over property graphs, why path semantics decide whether a query terminates, and where the ISO GQL standard and SQL/PGQ fit as of September 2026.
- 02 Triples, Ontologies and the Open World What the subject-predicate-object model buys, why the open world assumption changes what absence means, and where an ontology's constraints help and hurt.
- 03 Building a Graph from Unstructured Text The extraction pipeline from documents to triples, why open extraction produces an unusable graph, and the schema and validation decisions that determine whether the result is queryable.
- 04 Entity Resolution at Graph Scale Why matching records is quadratic and how blocking makes it tractable, the transitivity trap in clustering matches, and why this determines a knowledge graph's quality more than anything downstream.
- 05 Grounding Language Models in Structured Knowledge What a knowledge graph provides that vector retrieval cannot, the two integration patterns, and where the translation from language to structure fails.
- 06 Knowledge Graph Embeddings How representing entities and relations as vectors turns completion into a scoring problem, what each scoring function can and cannot express, and why evaluation in this area has been unreliable.
Recommender Systems Matrix factorisation, two-tower retrieval, ranking objectives, feedback loops and cold start. 12 concepts · 152 cards
- 01 Cold Start and Content-Based Hybrids Why a new user or item is invisible to collaborative filtering, how hybrid models build representations from metadata instead of interaction history, and the exploration cost that no content feature removes.
- 02 Matrix Factorisation and Implicit Feedback Learning low-rank user and item vectors from a sparse interaction matrix, and why the shift from ratings to clicks changes the loss, the negatives and the meaning of the output.
- 03 Semantic IDs for Recommendation Why recommenders hash item identifiers into meaningless buckets, how quantising a content embedding into a short tuple of discrete codes replaces that hash with an address that carries similarity, and what the second training stage costs you.
- 04 Collapsing the Retrieval and Ranking Cascade What a single end-to-end generative recommender buys in efficiency when it replaces the retrieve-prerank-rank pipeline, and what you give up by deleting the stage boundaries that business logic, calibration and debugging all live on.
- 05 Deep CTR Ranking Models: Wide & Deep, DCN and DLRM How ranking models for click-through prediction combine huge sparse embedding tables with explicit feature-interaction layers, what Wide & Deep, Deep & Cross and DLRM each assume about crosses, and why careful benchmarking shrank the differences between them.
- 06 Feedback Loops and Filter Bubbles A recommender trained on data it generated is optimising against its own past choices, which narrows what users see and makes offline evaluation systematically agree with the incumbent.
- 07 Generative Retrieval for Recommendation What changes when a model decodes an item identifier token by token instead of scoring a catalogue, why the index moves into the weights, and the cold-start collapse that the headline benchmark numbers hide.
- 08 Item Tokeniser Drift and Catalogue Updates Why moving the retrieval index into model weights turns every new item and every content-encoder upgrade into a continual-learning problem, and how much retrieval quality forgetting actually destroys.
- 09 Offline Evaluation and Sampled Metrics in Recommenders Why ranking against 100 sampled negatives can reverse which recommender looks best, how random splits leak the future into training, and what a decade of reproducibility studies says about reported progress.
- 10 Sequential Recommendation: SASRec and BERT4Rec Treating a user's history as an ordered sequence and predicting the next item with a transformer, and why the famous SASRec versus BERT4Rec comparison turned out to be about loss functions and training budgets rather than attention direction.
- 11 Sequential Transduction for Recommendation Why deep CTR models stopped improving when given more compute, how reformulating ranking as next-action prediction over one unified event stream restored a scaling curve, and where that curve flattens.
- 12 Two-Tower Retrieval and Candidate Generation Splitting the model so that item representations can be precomputed and searched with approximate nearest neighbours, which is what makes recommending from a hundred-million-item catalogue possible at all.
Tabular Deep Learning Why trees still win, attention over columns, prior-fitted networks and the benchmarks that decide the argument. 6 concepts · 67 cards
- 01 Attention Over Columns How transformer architectures are adapted to tables, what per-feature embeddings buy, and why the attention mechanism addresses the feature selection problem specifically.
- 02 Benchmarking Tabular Methods Honestly Why tabular comparisons disagree so persistently, the tuning asymmetry that produces most of the disagreement, and what a comparison needs to support its conclusion.
- 03 Deep Learning for High-Cardinality Categoricals The one tabular regime where networks clearly win, why embeddings handle millions of levels that trees cannot, and the engineering that dominates such systems.
- 04 Numerical Feature Embeddings for Tabular Models Why feeding a raw scalar into an MLP handicaps it on tabular data, how piecewise linear encodings and trainable periodic features turn each number into a vector, and what Gorishniy et al. (2022) measured when they did.
- 05 Prior-Fitted Networks and In-Context Tabular Learning How a model trained entirely on synthetic datasets can classify a real one without fitting, what approximating the Bayesian posterior in a forward pass means, and the constraints that follow.
- 06 The Inductive Bias Mismatch on Tabular Data The three properties of tabular data that neural networks handle badly and trees handle naturally, why this is a bias mismatch rather than a capacity problem, and what it implies for architecture design.