Zum Hauptinhalt springen
tsecurity.de LIVE
Echtzeit-Radar & Feeds
Alle RSS Feeds
👥 Community & Social
Sichere ProgrammierungKI half beim Finden: iOS 27 schließt mehr als 100 Sicherheitslücken(21.09.2026 um 06:00 Uhr)
Sichere ProgrammierungWhat Is Rowhammer? How Can Repeated Memory Access Flip Bits in RAM?(21.09.2026 um 07:12 Uhr)
Sichere Programmierungnpm publish Ignores .gitignore: The .npmignore Override Rule(21.09.2026 um 07:15 Uhr)
Sichere ProgrammierungAphelion Editor - A free node-based video / VFX editor(21.09.2026 um 07:21 Uhr)
Sichere ProgrammierungGovernance Attack Surface Review: OKX(21.09.2026 um 07:31 Uhr)
Sichere ProgrammierungJSM Portal Request Create Property Panel Submit(21.09.2026 um 07:34 Uhr)
Reverse Engineeringsearch instructions assembly easy (X86,RISCV,AARCH64,etc)(20.09.2026 um 15:44 Uhr)
Sichere ProgrammierungKI half beim Finden: iOS 27 schließt mehr als 100 Sicherheitslücken(21.09.2026 um 06:00 Uhr)
Sichere ProgrammierungWhat Is Rowhammer? How Can Repeated Memory Access Flip Bits in RAM?(21.09.2026 um 07:12 Uhr)
Sichere Programmierungnpm publish Ignores .gitignore: The .npmignore Override Rule(21.09.2026 um 07:15 Uhr)
Sichere ProgrammierungAphelion Editor - A free node-based video / VFX editor(21.09.2026 um 07:21 Uhr)
Sichere ProgrammierungGovernance Attack Surface Review: OKX(21.09.2026 um 07:31 Uhr)
Sichere ProgrammierungJSM Portal Request Create Property Panel Submit(21.09.2026 um 07:34 Uhr)
Reverse Engineeringsearch instructions assembly easy (X86,RISCV,AARCH64,etc)(20.09.2026 um 15:44 Uhr)
Intelligence View
⚡ tsecurity.de Intelligence

Debiasing Graph Neural Networks for Recommendation with Causal RL

Reagiere als Erste:r — dein Feedback zählt!

As part of my undergraduate research in Graph Neural Networks (GNNs) and Causal Inference, I've been exploring a major flaw in modern recommender systems: observational bias.

Standard recommendation algorithms—even state-of-the-art GNNs like LightGCN and NGCF—learn from biased data. Popular items get shown more often, which leads to more clicks, creating a feedback loop that reinforces popularity bias and buries niche items.

To solve this, I built an open-source framework that combines GNNs with Causal Reinforcement Learning to debias recommendations.

Here is how I approached it.

👋 Hi, I'm Tasfin Mahmud! I'm a CS Researcher at BRAC University and an open-source contributor. You can learn more about my work on my portfolio website or my GitHub.

🏗️ The Baseline GNNs

I started by implementing three solid baseline architectures in PyTorch Geometric (PyG):

  1. LightGCN: The minimalist approach that drops non-linear transformations.
  2. NGCF (Neural Graph Collaborative Filtering): Explicitly models high-order connectivities with feature interaction terms.
  3. GAT-CF: Graph Attention Networks adapted for collaborative filtering.

These models perform incredibly well on standard metrics. But there is a catch: if you evaluate them on observational data, the metrics look great only because the test data shares the same exposure bias as the training data.

🧪 Injecting Causal RL

To break the popularity loop, I implemented four complementary causal debiasing techniques.

1. Inverse Propensity Scoring (IPS)

The simplest way to fix exposure bias is to reweight the Bayesian Personalised Ranking (BPR) training loss. IPS divides the loss for each item by its exposure probability. Rarely shown items receive a higher gradient signal, while mega-popular items are scaled down.

2. Causal Embeddings (CausE)

Here, the model maintains two separate embedding spaces:

  • A factual space (learned from the biased data)
  • A counterfactual space (representing uniform exposure)

A discrepancy regularizer pulls the factual representations toward the unbiased counterfactual ones, preventing the model from overfitting to the exposure distribution.

3. Causal Policy Gradient

Treating recommendations as a sequential decision-making problem, I used the REINFORCE algorithm. The core innovation here is Causal Reward Shaping: decomposing observed rewards into the "true preference" (causal component) and the "popularity bias" (confounding component). Using Doubly Robust (DR) estimation makes learning from logged data much more stable.

4. Causal Discovery

How do we know what the confounders are if they aren't explicitly measured? I implemented a causal discovery module using Truncated SVD on the exposure matrix to automatically identify latent confounding factors, which are then integrated into the reward shaping process.

📊 The Results

I benchmarked these approaches using LightGCN on the MovieLens 100k dataset:

Model Mode Recall@20 NDCG@20 Notes
Standard (Baseline) 0.1676 0.1624 Standard biased observational learning
IPS Debiasing 0.1453 0.1543 Re-weights rare items; expected to drop on biased test data
CausE 0.1675 0.1625 Regularized against uniform exposure
Causal PG (DR) 0.1593 0.1602 Doubly robust policy gradient

(Note: Evaluating debiased models on standard biased test sets results in lower raw metric scores because the test set shares the exposure bias. Unbiased logging data is required to see the true lift).

💡 The Takeaway

GNNs are powerful tools for recommendation, but without causal inference, they are simply learning to amplify existing biases in your dataset. By utilizing techniques like IPS and Causal Policy Gradients, we can build recommendation systems that truly understand user preference rather than just popularity.

🔗 Check out the full framework on my GitHub:
gnn-collaborative-filtering

🔗 Learn more about my research and open-source work:
tasfinmahmud.github.io

Let me know in the comments if you've worked with Causal Inference for recommendation systems!

Ähnliche Beiträge
🔍 Verwandte News

Auch interessante Nachrichten Debiasing Graph Neural Networks for Recommendation with Causal RL

Thematisch verwandte Begriffe: Debiasing, Graph, Neural, Networks · 6 Treffer

Laden...

Videos werden geladen ...

Laden...

Beiträge werden geladen ...

Laden...

Videos werden geladen ...

Laden...

Beiträge werden geladen ...

Laden...

Videos werden geladen ...

Laden...

Beiträge werden geladen ...

Laden...

Videos werden geladen ...

Laden...

Beiträge werden geladen ...

Laden...

Videos werden geladen ...

Zum Aktualisieren ziehen
ZERO-DAY CVE-2026-94111 | Tencent BrowserSkill through 0.3.0 contains an authentication bypass vul…
Advisory →
TTS Reader • tsecurity.de Voice
tsecurity.de Icon
tsecurity.de App
Offline-Lesen, Eilmeldungen & 0ms Ladezeit

Installiere tsecurity.de direkt auf deinen Home-Bildschirm für das ultimative Vollbild-Magazinerlebnis ohne Browser-Leisten.

Nächster Beitrag
Themen-Radar & Intelligence Matrix
Echtzeit-Taxonomie nach Angriffsvektoren & Plattformen

tsecurity.de Live Threat Radar

🔴 LIVE RADAR
MONITORING
AKTIV
CVE-DATENBANK
LIVE
🔍
Community Radar & Live Chat
Sentinel Bot online • Live-Stream
Dein Cluster: Security Explorer
Match:
lädt…
Verbindung zum Community-Stream wird aufgebaut...
Bearbeitungsmodus — Senden überschreibt deine Nachricht
Community-Puls — was gerade passiert
lädt…
Aktivitäten deiner Analysten
lädt…
Neues Thema oder Eilmeldung einreichen

Reiche interessante Links, Zero-Days oder Debatten ein. Die Community entscheidet per Upvote über die Veröffentlichung.

Heiß diskutierte Einreichungen
🔖 Gespeicherte Artikel
📂 Keine gespeicherten Artikel vorhanden.
Zurück Ziehen Vor
Links: vorheriger Artikel Rechts: nächster Artikel unten: schließen
News NIS-2 Frühwarnung Tier-1 Intel ⏱️ 3 Min vor 10 Min
Artikeldaten werden geladen...

Zurück: vorheriger Vor: nächster
↗ Original-Quelle
Social Reaktionen Deine Reaktion zählt
Einstufung & Relevanz-Poll 0 Stimmen
In sozialen Netzwerken teilen 1-Klick