Interpret the Internal States of Recommendation Model with Sparse Autoencoder
- URL: http://arxiv.org/abs/2411.06112v1
- Date: Sat, 09 Nov 2024 08:22:31 GMT
- Title: Interpret the Internal States of Recommendation Model with Sparse Autoencoder
- Authors: Jiayin Wang, Xiaoyu Zhang, Weizhi Ma, Min Zhang,
- Abstract summary: RecSAE is an automatic, generalizable probing method for interpreting the internal states of Recommendation models.
We train an autoencoder with sparsity constraints to reconstruct internal activations of recommendation models.
We automated the construction of concept dictionaries based on the relationship between latent activations and input item sequences.
- Score: 26.021277330699963
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Explainable recommendation systems are important to enhance transparency, accuracy, and fairness. Beyond result-level explanations, model-level interpretations can provide valuable insights that allow developers to optimize system designs and implement targeted improvements. However, most current approaches depend on specialized model designs, which often lack generalization capabilities. Given the various kinds of recommendation models, existing methods have limited ability to effectively interpret them. To address this issue, we propose RecSAE, an automatic, generalizable probing method for interpreting the internal states of Recommendation models with Sparse AutoEncoder. RecSAE serves as a plug-in module that does not affect original models during interpretations, while also enabling predictable modifications to their behaviors based on interpretation results. Firstly, we train an autoencoder with sparsity constraints to reconstruct internal activations of recommendation models, making the RecSAE latents more interpretable and monosemantic than the original neuron activations. Secondly, we automated the construction of concept dictionaries based on the relationship between latent activations and input item sequences. Thirdly, RecSAE validates these interpretations by predicting latent activations on new item sequences using the concept dictionary and deriving interpretation confidence scores from precision and recall. We demonstrate RecSAE's effectiveness on two datasets, identifying hundreds of highly interpretable concepts from pure ID-based models. Latent ablation studies further confirm that manipulating latent concepts produces corresponding changes in model output behavior, underscoring RecSAE's utility for both understanding and targeted tuning recommendation models. Code and data are publicly available at https://github.com/Alice1998/RecSAE.
Related papers
- LatentQA: Teaching LLMs to Decode Activations Into Natural Language [72.87064562349742]
We introduce LatentQA, the task of answering open-ended questions about model activations in natural language.
We propose Latent Interpretation Tuning (LIT), which finetunes a decoder LLM on a dataset of activations and associated question-answer pairs.
Our decoder also specifies a differentiable loss that we use to control models, such as debiasing models on stereotyped sentences and controlling the sentiment of generations.
arXiv Detail & Related papers (2024-12-11T18:59:33Z) - Constructing Concept-based Models to Mitigate Spurious Correlations with Minimal Human Effort [31.992947353231564]
Concept Bottleneck Models (CBMs) can provide a principled way of disclosing and guiding model behaviors through human-understandable concepts.
We propose a novel framework designed to exploit pre-trained models while being immune to these biases, thereby reducing vulnerability to spurious correlations.
We evaluate the proposed method on multiple datasets, and the results demonstrate its effectiveness in reducing model reliance on spurious correlations while preserving its interpretability.
arXiv Detail & Related papers (2024-07-12T03:07:28Z) - Self-supervised Interpretable Concept-based Models for Text Classification [9.340843984411137]
This paper proposes a self-supervised Interpretable Concept Embedding Models (ICEMs)
We leverage the generalization abilities of Large-Language Models to predict the concepts labels in a self-supervised way.
ICEMs can be trained in a self-supervised way achieving similar performance to fully supervised concept-based models and end-to-end black-box ones.
arXiv Detail & Related papers (2024-06-20T14:04:53Z) - Understanding Before Recommendation: Semantic Aspect-Aware Review Exploitation via Large Language Models [53.337728969143086]
Recommendation systems harness user-item interactions like clicks and reviews to learn their representations.
Previous studies improve recommendation accuracy and interpretability by modeling user preferences across various aspects and intents.
We introduce a chain-based prompting approach to uncover semantic aspect-aware interactions.
arXiv Detail & Related papers (2023-12-26T15:44:09Z) - RecExplainer: Aligning Large Language Models for Explaining Recommendation Models [50.74181089742969]
Large language models (LLMs) have demonstrated remarkable intelligence in understanding, reasoning, and instruction following.
This paper presents the initial exploration of using LLMs as surrogate models to explain black-box recommender models.
To facilitate an effective alignment, we introduce three methods: behavior alignment, intention alignment, and hybrid alignment.
arXiv Detail & Related papers (2023-11-18T03:05:43Z) - Interpreting and Controlling Vision Foundation Models via Text
Explanations [45.30541722925515]
We present a framework for interpreting vision transformer's latent tokens with natural language.
Our approach enables understanding of model visual reasoning procedure without needing additional model training or data collection.
arXiv Detail & Related papers (2023-10-16T17:12:06Z) - Evaluating and Explaining Large Language Models for Code Using Syntactic
Structures [74.93762031957883]
This paper introduces ASTxplainer, an explainability method specific to Large Language Models for code.
At its core, ASTxplainer provides an automated method for aligning token predictions with AST nodes.
We perform an empirical evaluation on 12 popular LLMs for code using a curated dataset of the most popular GitHub projects.
arXiv Detail & Related papers (2023-08-07T18:50:57Z) - Disentanglement via Latent Quantization [60.37109712033694]
In this work, we construct an inductive bias towards encoding to and decoding from an organized latent space.
We demonstrate the broad applicability of this approach by adding it to both basic data-re (vanilla autoencoder) and latent-reconstructing (InfoGAN) generative models.
arXiv Detail & Related papers (2023-05-28T06:30:29Z) - Interpretable Sentence Representation with Variational Autoencoders and
Attention [0.685316573653194]
We develop methods to enhance the interpretability of recent representation learning techniques in natural language processing (NLP)
We leverage Variational Autoencoders (VAEs) due to their efficiency in relating observations to latent generative factors.
We build two models with inductive bias to separate information in latent representations into understandable concepts without annotated data.
arXiv Detail & Related papers (2023-05-04T13:16:15Z) - Explaining Language Models' Predictions with High-Impact Concepts [11.47612457613113]
We propose a complete framework for extending concept-based interpretability methods to NLP.
We optimize for features whose existence causes the output predictions to change substantially.
Our method achieves superior results on predictive impact, usability, and faithfulness compared to the baselines.
arXiv Detail & Related papers (2023-05-03T14:48:27Z) - ProtoVAE: A Trustworthy Self-Explainable Prototypical Variational Model [18.537838366377915]
ProtoVAE is a variational autoencoder-based framework that learns class-specific prototypes in an end-to-end manner.
It enforces trustworthiness and diversity by regularizing the representation space and introducing an orthonormality constraint.
arXiv Detail & Related papers (2022-10-15T00:42:13Z) - Explain, Edit, and Understand: Rethinking User Study Design for
Evaluating Model Explanations [97.91630330328815]
We conduct a crowdsourcing study, where participants interact with deception detection models that have been trained to distinguish between genuine and fake hotel reviews.
We observe that for a linear bag-of-words model, participants with access to the feature coefficients during training are able to cause a larger reduction in model confidence in the testing phase when compared to the no-explanation control.
arXiv Detail & Related papers (2021-12-17T18:29:56Z) - Combining Discrete Choice Models and Neural Networks through Embeddings:
Formulation, Interpretability and Performance [10.57079240576682]
This study proposes a novel approach that combines theory and data-driven choice models using Artificial Neural Networks (ANNs)
In particular, we use continuous vector representations, called embeddings, for encoding categorical or discrete explanatory variables.
Our models deliver state-of-the-art predictive performance, outperforming existing ANN-based models while drastically reducing the number of required network parameters.
arXiv Detail & Related papers (2021-09-24T15:55:31Z) - InteL-VAEs: Adding Inductive Biases to Variational Auto-Encoders via
Intermediary Latents [60.785317191131284]
We introduce a simple and effective method for learning VAEs with controllable biases by using an intermediary set of latent variables.
In particular, it allows us to impose desired properties like sparsity or clustering on learned representations.
We show that this, in turn, allows InteL-VAEs to learn both better generative models and representations.
arXiv Detail & Related papers (2021-06-25T16:34:05Z) - Model Learning with Personalized Interpretability Estimation (ML-PIE) [2.862606936691229]
High-stakes applications require AI-generated models to be interpretable.
Current algorithms for the synthesis of potentially interpretable models rely on objectives or regularization terms.
We propose an approach for the synthesis of models that are tailored to the user.
arXiv Detail & Related papers (2021-04-13T09:47:48Z) - A Minimalist Dataset for Systematic Generalization of Perception,
Syntax, and Semantics [131.93113552146195]
We present a new dataset, Handwritten arithmetic with INTegers (HINT), to examine machines' capability of learning generalizable concepts.
In HINT, machines are tasked with learning how concepts are perceived from raw signals such as images.
We undertake extensive experiments with various sequence-to-sequence models, including RNNs, Transformers, and GPT-3.
arXiv Detail & Related papers (2021-03-02T01:32:54Z) - Autoencoding Variational Autoencoder [56.05008520271406]
We study the implications of this behaviour on the learned representations and also the consequences of fixing it by introducing a notion of self consistency.
We show that encoders trained with our self-consistency approach lead to representations that are robust (insensitive) to perturbations in the input introduced by adversarial attacks.
arXiv Detail & Related papers (2020-12-07T14:16:14Z) - Explaining and Improving Model Behavior with k Nearest Neighbor
Representations [107.24850861390196]
We propose using k nearest neighbor representations to identify training examples responsible for a model's predictions.
We show that kNN representations are effective at uncovering learned spurious associations.
Our results indicate that the kNN approach makes the finetuned model more robust to adversarial inputs.
arXiv Detail & Related papers (2020-10-18T16:55:25Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.