Search Results for author:
Found 34 papers, 11 papers with code
Position: Mechanistic Interpretability Should Prioritize Feature Consistency in SAEs
Sparse Autoencoders (SAEs) are a prominent tool in mechanistic interpretability (MI) for decomposing neural network activations into interpretable features.
Nonparametric Factor Analysis and Beyond
Nearly all identifiability results in unsupervised representation learning inspired by, e. g., independent component analysis, factor analysis, and causal representation learning, rely on assumptions of additive independent noise or noiseless regimes.
Type Information-Assisted Self-Supervised Knowledge Graph Denoising
For the specific task of noise detection, the discrepancy between the reconstruction results and the input knowledge graph provides an opportunity for denoising, which is facilitated by the type consistency embedded in our method.
Synergy Between Sufficient Changes and Sparse Mixing Procedure for Disentangled Representation Learning
Some approaches rely on sufficient changes on the distribution of latent variables indicated by auxiliary variables such as domain indices, but acquiring enough domains is often challenging.
Synthetic Poisoning Attacks: The Impact of Poisoned MRI Image on U-Net Brain Tumor Segmentation
Deep learning-based medical image segmentation models, such as U-Net, rely on high-quality annotated datasets to achieve accurate predictions.
Identification of Nonparametric Dynamic Causal Structure and Latent Process in Climate System
The study of learning causal structure with latent variables has advanced the understanding of the world by uncovering causal relationships and latent factors, e. g., Causal Representation Learning (CRL).
SmartCLIP: Modular Vision-language Alignment with Identification Guarantees
On the other hand, directly aligning long captions with images can lead to the retention of entangled details, preventing the model from learning disentangled, atomic concepts -- ultimately limiting its generalization on certain downstream tasks involving short prompts.
Causal Representation Learning from Multimodal Biomedical Observations
Theoretically, we consider a nonparametric latent distribution (c. f., parametric assumptions in previous work) that allows for causal relationships across potentially different modalities.
Identifying Selections for Unsupervised Subtask Discovery
When solving long-horizon tasks, it is intriguing to decompose the high-level task into subtasks.
Causality for Large Language Models
How to embed causality into the training process of LLMs and build more general and intelligent models remains unexplored.
SciSafeEval: A Comprehensive Benchmark for Safety Alignment of Large Language Models in Scientific Tasks
To address these limitations, we introduce SciSafeEval, a comprehensive benchmark designed to evaluate the safety alignment of LLMs across a range of scientific tasks.
Causal Temporal Representation Learning with Nonstationary Sparse Transition
Based on the theoretical result, we introduce a novel framework, Causal Temporal Representation Learning with Nonstationary Sparse Transition (CtrlNS), designed to leverage the constraints on transition sparsity and conditional independence to reliably identify both distribution shifts and latent factors.
On the Identifiability of Sparse ICA without Assuming Non-Gaussianity
To accommodate Gaussian sources, we develop an identifiability theory that relies on second-order statistics without imposing further preconditions on the distribution of sources, by introducing novel assumptions on the connective structure from sources to observed variables.
Cloud Atlas: Efficient Fault Localization for Cloud Systems using Language Models and Causal Insight
We evaluate Atlas across a range of fault localization scenarios and demonstrate that Atlas is capable of generating causal graphs in a scalable and generalizable manner, with performance that far surpasses that of data-driven algorithms and is commensurate to the ground-truth baseline.
Detecting and Identifying Selection Structure in Sequential Data
Therefore, rather than merely viewing it as a bias, we explore the causal structure of selection in sequential data to delve deeper into the complete causal process.
Local Causal Discovery with Linear non-Gaussian Cyclic Models
Local causal discovery is of great practical significance, as there are often situations where the discovery of the global causal structure is unnecessary, and the interest lies solely on a single target variable.
Causal Representation Learning from Multiple Distributions: A General Setting
We show that under the sparsity constraint on the recovered graph over the latent variables and suitable sufficient change conditions on the causal influences, interestingly, one can recover the moralized graph of the underlying directed acyclic graph, and the recovered latent variables and their relations are related to the underlying causal model in a specific, nontrivial way.
A Versatile Causal Discovery Framework to Allow Causally-Related Hidden Variables
Most existing causal discovery methods rely on the assumption of no latent confounders, limiting their applicability in solving real-life problems.
A Comparative Study of AI-Generated (GPT-4) and Human-crafted MCQs in Programming Education
While there is a growing body of research in computing education on utilizing large language models (LLMs) in generation and engagement with coding exercises, the use of LLMs for generating programming MCQs has not been extensively explored.
Causal-learn: Causal Discovery in Python
Causal discovery aims at revealing causal relations from observational data, which is a fundamental task in science and engineering.
Partial Identifiability for Domain Adaptation
In general, without further assumptions, the joint distribution of the features and the label is not identifiable in the target domain.
Understanding Breast Cancer Survival: Using Causality and Language Models on Multi-omics Data
The need for more usable and explainable machine learning models in healthcare increases the importance of developing and utilizing causal discovery algorithms, which aim to discover causal relations by analyzing observational data.
Generalized Precision Matrix for Scalable Estimation of Nonparametric Markov Networks
A Markov network characterizes the conditional independence structure, or Markov property, among a set of random variables.
Learning Task-Aware Effective Brain Connectivity for fMRI Analysis with Graph Neural Networks
To better adapt GNNs for fMRI analysis, we propose TBDS, an end-to-end framework based on \underline{T}ask-aware \underline{B}rain connectivity \underline{D}AG (short for Directed Acyclic Graph) \underline{S}tructure generation for fMRI analysis.
Whole Page Unbiased Learning to Rank
To address the above challenges, we propose a Bias Agnostic whole-page unbiased Learning to rank algorithm, named BAL, to automatically find the user behavior model with causal discovery and mitigate the biases induced by multiple SERP features with no specific design.
On the Identifiability of Nonlinear ICA: Sparsity and Beyond
We show that under specific instantiations of such constraints, the independent latent sources can be identified from their nonlinear mixtures up to a permutation and a component-wise transformation, thus achieving nontrivial identifiability of nonlinear ICA without auxiliary variables.
Reliable Causal Discovery with Improved Exact Search and Weaker Assumptions
Many of the causal discovery methods rely on the faithfulness assumption to guarantee asymptotic correctness.
Source Free Unsupervised Graph Domain Adaptation
To address the non-trivial adaptation challenges in this practical scenario, we propose a model-agnostic algorithm called SOGA for domain adaptation to fully exploit the discriminative ability of the source model while preserving the consistency of structural proximity on the target graph.
Learning Elastic Embeddings for Customizing On-Device Recommenders
The core idea is to compose elastic embeddings for each item, where an elastic embedding is the concatenation of a set of embedding blocks that are carefully chosen by an automated search function.
Cold-start Sequential Recommendation via Meta Learner
As there is generally no side information in the setting of sequential recommendation task, previous cold-start methods could not be applied when only user-item interactions are available.
Heterogeneous Graph Collaborative Filtering
In this work, we propose to model user-item interactions as a heterogeneous graph which consists of not only user-item edges indicating their interaction but also user-user edges indicating their similarity.
DGTN: Dual-channel Graph Transition Network for Session-based Recommendation
These item transitions include potential collaborative information and reflect similar behavior patterns, which we assume may help with the recommendation for the target session.
Ranked #6 on
Session-Based Recommendations
on Diginetica
Long-tail Session-based Recommendation
Session-based recommendation focuses on the prediction of user actions based on anonymous sessions and is a necessary method in the lack of user historical data.
Balancing Multi-level Interactions for Session-based Recommendation
For mining the new data without breaking the equilibrium of the model between different interactions, we construct an intra-session graph and an inter-session graph for the current session.
