skip to main content


This content will become publicly available on May 6, 2025

Title: DIRECT: Dual Interpretable Recommendation with Multi-aspect Word Attribution

Recommending products to users with intuitive explanations helps improve the system in transparency, persuasiveness, and satisfaction. Existing interpretation techniques include post-hoc methods and interpretable modeling. The former category could quantitatively analyze input contribution to model prediction but has limited interpretation faithfulness, while the latter could explain model internal mechanisms but may not directly attribute model predictions to input features. In this study, we propose a novelDualInterpretableRecommendation model called DIRECT, which integrates ideas of the two interpretation categories to inherit their advantages and avoid limitations. Specifically, DIRECT makes use of item descriptions as explainable evidence for recommendation. First, similar to the post-hoc interpretation, DIRECT could attribute the prediction of a user preference score to textual words of the item descriptions. The attribution of each word is related to its sentiment polarity and word importance, where a word is important if it corresponds to an item aspect that the user is interested in. Second, to improve the interpretability of embedding space, we propose to extract high-level concepts from embeddings, where each concept corresponds to an item aspect. To learn discriminative concepts, we employ a concept-bottleneck layer, and maximize the coding rate reduction on word-aspect embeddings by leveraging a word-word affinity graph extracted from a pre-trained language model. In this way, DIRECT simultaneously achieves faithful attribution and usable interpretation of embedding space. We also show that DIRECT achieves linear inference time complexity regarding the length of item reviews. We conduct experiments including ablation studies on five real-world datasets. Quantitative analysis, visualizations, and case studies verify the interpretability of DIRECT. Our code is available at:https://github.com/JacksonWuxs/DIRECT.

 
more » « less
Award ID(s):
2223768
PAR ID:
10520420
Author(s) / Creator(s):
; ; ; ;
Publisher / Repository:
ACM
Date Published:
Journal Name:
ACM Transactions on Intelligent Systems and Technology
ISSN:
2157-6904
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. Abstract Background

    Protein S-nitrosylation (SNO) plays a key role in transferring nitric oxide-mediated signals in both animals and plants and has emerged as an important mechanism for regulating protein functions and cell signaling of all main classes of protein. It is involved in several biological processes including immune response, protein stability, transcription regulation, post translational regulation, DNA damage repair, redox regulation, and is an emerging paradigm of redox signaling for protection against oxidative stress. The development of robust computational tools to predict protein SNO sites would contribute to further interpretation of the pathological and physiological mechanisms of SNO.

    Results

    Using an intermediate fusion-based stacked generalization approach, we integrated embeddings from supervised embedding layer and contextualized protein language model (ProtT5) and developed a tool called pLMSNOSite (protein language model-based SNO site predictor). On an independent test set of experimentally identified SNO sites, pLMSNOSite achieved values of 0.340, 0.735 and 0.773 for MCC, sensitivity and specificity respectively. These results show that pLMSNOSite performs better than the compared approaches for the prediction of S-nitrosylation sites.

    Conclusion

    Together, the experimental results suggest that pLMSNOSite achieves significant improvement in the prediction performance of S-nitrosylation sites and represents a robust computational approach for predicting protein S-nitrosylation sites. pLMSNOSite could be a useful resource for further elucidation of SNO and is publicly available athttps://github.com/KCLabMTU/pLMSNOSite.

     
    more » « less
  2. ord embeddings are commonly used to measure word-level semantic similarity in text, especially in direct word- to-word comparisons. However, the relationships between words in the embedding space are often viewed as approximately linear and concepts comprised of multiple words are a sort of linear combination. In this paper, we demonstrate that this is not generally true and show how the relationships can be better captured by leveraging the topology of the embedding space. We propose a technique for directly computing new vectors representing multiple words in a way that naturally combines them into a new, more consistent space where distance better correlates to similarity. We show that this technique works well for natural language, even when it comprises multiple words, on a simple task derived from WordNet synset descriptions and examples of words. Thus, the generated vectors better represent complex concepts in the word embedding space. 
    more » « less
  3. Abstract

    Diffusion models excel at text-to-image generation, especially in subject-driven generation for personalized images. However, existing methods are inefficient due to the subject-specific fine-tuning, which is computationally intensive and hampers efficient deployment. Moreover, existing methods struggle with multi-subject generation as they often blend identity among subjects. We present FastComposer which enables efficient, personalized, multi-subject text-to-image generation without fine-tuning. FastComposer uses subject embeddings extracted by an image encoder to augment the generic text conditioning in diffusion models, enabling personalized image generation based on subject images and textual instructionswith only forward passes. To address the identity blending problem in the multi-subject generation, FastComposer proposescross-attention localizationsupervision during training, enforcing the attention of reference subjects localized to the correct regions in the target images. Naively conditioning on subject embeddings results in subject overfitting. FastComposer proposesdelayed subject conditioningin the denoising step to maintain both identity and editability in subject-driven image generation. FastComposer generates images of multiple unseen individuals with different styles, actions, and contexts. It achieves 300$$\times $$×–2500$$\times $$×speedup compared to fine-tuning-based methods and requires zero extra storage for new subjects. FastComposer paves the way for efficient, personalized, and high-quality multi-subject image creation. Code, model, and dataset are available here (https://github.com/mit-han-lab/fastcomposer).

     
    more » « less
  4. Abstract

    The Molecular Sciences Software Institute's (MolSSI) Quantum Chemistry Archive (QCArchive) project is an umbrella name that covers both a central server hosted by MolSSI for community data and the Python‐based software infrastructure that powers automated computation and storage of quantum chemistry (QC) results. The MolSSI‐hosted central server provides the computational molecular sciences community a location to freely access tens of millions of QC computations for machine learning, methodology assessment, force‐field fitting, and more through a Python interface. Facile, user‐friendly mining of the centrally archived quantum chemical data also can be achieved through web applications found athttps://qcarchive.molssi.org. The software infrastructure can be used as a standalone platform to compute, structure, and distribute hundreds of millions of QC computations for individuals or groups of researchers at any scale. The QCArchiveInfrastructureis open‐source (BSD‐3C), code repositories can be found athttps://github.com/MolSSI, and releases can be downloaded via PyPI and Conda.

    This article is categorized under:

    Electronic Structure Theory > Ab Initio Electronic Structure Methods

    Software > Quantum Chemistry

    Data Science > Computer Algorithms and Programming

     
    more » « less
  5. Abstract OPEN RESEARCH BADGES

    This article has been awarded Open Materials, Open Data, Preregistered Research Designs Badges. All materials and data are publicly accessible via the Open Science Framework athttps://doi.org/10.6084/m9.figshare.8028875.v1,https://github.com/lotteanna/defence_adaptation,https://doi.org/10.1101/435271.

     
    more » « less