Search Results for author:
Found 47 papers, 16 papers with code
Causal Discovery from Poisson Branching Structural Causal Model Using High-Order Cumulant with Path Analysis
Fortunately, in this work, we found that the causal order from $X$ to its child $Y$ is identifiable if $X$ is a root vertex and has at least two directed paths to $Y$, or the ancestor of $X$ with the most directed path to $X$ has a directed path to $Y$ without passing $X$.
From Large to Tiny: Distilling and Refining Mathematical Expertise for Math Word Problems with Weakly Supervision
In light of these challenges, we introduce an innovative two-stage framework that adeptly transfers mathematical Expertise from large to tiny language models.
Debiased Model-based Interactive Recommendation
Existing model-based interactive recommendation systems are trained by querying a world model to capture the user preference, but learning the world model from historical logged data will easily suffer from bias issues such as popularity bias and sampling bias.
When and How: Learning Identifiable Latent States for Nonstationary Time Series Forecasting
To solve this problem, we propose to learn IDentifiable latEnt stAtes (IDEA) to detect when the distribution shifts occur.
Unifying Invariance and Spuriousity for Graph Out-of-Distribution via Probability of Necessity and Sufficiency
Under mild conditions, we show that the invariant subgraph can be extracted by minimizing an upper bound, which is built on the theoretical advance of probability of necessity and sufficiency.
Feature Attribution with Necessity and Sufficiency via Dual-stage Perturbation Test for Causal Explanation
We investigate the problem of explainability in machine learning. To address this problem, Feature Attribution Methods (FAMs) measure the contribution of each feature through a perturbation test, where the difference in prediction is compared under different perturbations. However, such perturbation tests may not accurately distinguish the contributions of different features, when their change in prediction is the same after perturbation. In order to enhance the ability of FAMs to distinguish different features' contributions in this challenging setting, we propose to utilize the probability (PNS) that perturbing a feature is a necessary and sufficient cause for the prediction to change as a measure of feature importance. Our approach, Feature Attribution with Necessity and Sufficiency (FANS), computes the PNS via a perturbation test involving two stages (factual and interventional). In practice, to generate counterfactual samples, we use a resampling-based approach on the observed samples to approximate the required conditional distribution. Finally, we combine FANS and gradient-based optimization to extract the subset with the largest PNS. We demonstrate that FANS outperforms existing feature attribution methods on six benchmarks.
Learning by Doing: An Online Causal Reinforcement Learning Framework with Causal-Aware Policy
As a key component to intuitive cognition and reasoning solutions in human intelligence, causal knowledge provides great potential for reinforcement learning (RL) agents' interpretability towards decision-making by helping reduce the searching space.
Where and How to Attack? A Causality-Inspired Recipe for Generating Counterfactual Adversarial Examples
By considering the underappreciated causal generating process, first, we pinpoint the source of the vulnerability of DNNs via the lens of causality, then give theoretical results to answer \emph{where to attack}.
Identification of Causal Structure with Latent Variables Based on Higher Order Cumulants
Despite the emergence of numerous methods aimed at addressing this challenge, they are not fully identified to the structure that two observed variables are influenced by one latent variable and there might be a directed edge in between.
Identification of Causal Structure in the Presence of Missing Data with Additive Noise Model
With this observation, we aim to investigate the identification problem of learning causal structure from missing data under an additive noise model with different missingness mechanisms, where the `no self-masking missingness' assumption can be eliminated appropriately.
Identifying Semantic Component for Robust Molecular Property Prediction
Specifically, we first formulate the data generation process from the atom level to the molecular level, where the latent space is split into SI substructures, SR substructures, and SR atom variables.
Subspace Identification for Multi-Source Domain Adaptation
To mitigate the need for these strict assumptions, we propose a subspace identification theory that guarantees the disentanglement of domain-invariant and domain-specific variables under less restrictive constraints regarding domain numbers and transformation properties, thereby facilitating domain adaptation by minimizing the impact of domain shifts on invariant variables.
Generalized Independent Noise Condition for Estimating Causal Structure with Latent Variables
To address this, we propose a Generalized Independent Noise (GIN) condition for linear non-Gaussian acyclic causal models that incorporate latent variables, which establishes the independence between a linear combination of certain measured variables and some other measured variables.
Generalization bound for estimating causal effects from observational network data
To fill this gap, we derive a generalization bound for causal effect estimation in network scenarios by exploiting 1) the reweighting schema based on joint propensity score and 2) the representation learning schema based on Integral Probability Metric (IPM).
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.
TNPAR: Topological Neural Poisson Auto-Regressive Model for Learning Granger Causal Structure from Event Sequences
assumption is often violated due to the inherent dependencies among the event sequences.
Causal Discovery with Latent Confounders Based on Higher-Order Cumulants
In light of the power of the closed-form solution to OICA corresponding to the One-Latent-Component structure, we formulate a way to estimate the mixing matrix using the higher-order cumulants, and further propose the testable One-Latent-Component condition to identify the latent variables and determine causal orders.
Structural Hawkes Processes for Learning Causal Structure from Discrete-Time Event Sequences
Learning causal structure among event types from discrete-time event sequences is a particularly important but challenging task.
A Survey on Causal Reinforcement Learning
While Reinforcement Learning (RL) achieves tremendous success in sequential decision-making problems of many domains, it still faces key challenges of data inefficiency and the lack of interpretability.
On the Probability of Necessity and Sufficiency of Explaining Graph Neural Networks: A Lower Bound Optimization Approach
To address the non-identifiability of PNS, we resort to a lower bound of PNS that can be optimized via counterfactual estimation, and propose a framework of Necessary and Sufficient Explanation for GNN (NSEG) via optimizing that lower bound.
Long-term Causal Effects Estimation via Latent Surrogates Representation Learning
Estimating long-term causal effects based on short-term surrogates is a significant but challenging problem in many real-world applications, e. g., marketing and medicine.
Time-Series Domain Adaptation via Sparse Associative Structure Alignment: Learning Invariance and Variance
Based on this inspiration, we investigate the domain-invariant unweighted sparse associative structures and the domain-variant strengths of the structures.
REST: Debiased Social Recommendation via Reconstructing Exposure Strategies
By explicitly Reconstructing Exposure STrategies (REST in short), we formalize the recommendation problem as the counterfactual reasoning and propose the debiased social recommendation method.
Motif Graph Neural Network
However, standard GNNs in the neighborhood aggregation paradigm suffer from limited discriminative power in distinguishing \emph{high-order} graph structures as opposed to \emph{low-order} structures.
Domain Adaptation with Invariant Representation Learning: What Transformations to Learn?
We provide reasoning why when the supports of the source and target data from overlap, any map of $X$ that is fixed across domains may not be suitable for domain adaptation via invariant features.
CCSL: A Causal Structure Learning Method from Multiple Unknown Environments
This method simultaneously integrates the following two tasks: 1) clustering samples of the subjects with the same causal mechanism into different groups; 2) learning causal structures from the samples within the group.
TEA: A Sequential Recommendation Framework via Temporally Evolving Aggregations
To achieve this, we firstly formalize sequential recommendation as a problem to estimate conditional probability given temporal dynamic heterogeneous graphs and user behavior sequences.
Transferable Time-Series Forecasting under Causal Conditional Shift
In order to address these challenges, we analyze variational conditional dependencies in time-series data and find that the causal structures are usually stable among domains, and further raise the causal conditional shift assumption.
SADGA: Structure-Aware Dual Graph Aggregation Network for Text-to-SQL
The key lies in the generalizability of (i) the encoding method to model the question and the database schema and (ii) the question-schema linking method to learn the mapping between words in the question and tables/columns in the database schema.
Ranked #4 on
Text-To-SQL
on spider
(Exact Match Accuracy (Test) metric)
Graph Domain Adaptation: A Generative View
Based on this assumption, we propose a disentanglement-based unsupervised domain adaptation method for the graph-structured data, which applies variational graph auto-encoders to recover these latent variables and disentangles them via three supervised learning modules.
On the Role of Entropy-based Loss for Learning Causal Structures with Continuous Optimization
Causal discovery from observational data is an important but challenging task in many scientific fields.
THP: Topological Hawkes Processes for Learning Causal Structure on Event Sequences
We further propose a causal structure learning method on THP in a likelihood framework.
FRITL: A Hybrid Method for Causal Discovery in the Presence of Latent Confounders
The first step of our method uses the FCI procedure, which allows confounders and is able to produce asymptotically correct results.
Semi-Supervised Disentangled Framework for Transferable Named Entity Recognition
In the proposed framework, the domain-specific information is integrated with the domain-specific latent variables by using a domain predictor.
Learning Disentangled Semantic Representation for Domain Adaptation
Different from previous efforts on the entangled feature space, we aim to extract the domain invariant semantic information in the latent disentangled semantic representation (DSR) of the data.
Time Series Domain Adaptation via Sparse Associative Structure Alignment
To reduce the difficulty in the discovery of causal structure, we relax it to the sparse associative structure and propose a novel sparse associative structure alignment model for domain adaptation.
Generalized Independent Noise Condition for Estimating Latent Variable Causal Graphs
Despite its success in certain domains, most existing methods focus on causal relations between observed variables, while in many scenarios the observed ones may not be the underlying causal variables (e. g., image pixels), but are generated by latent causal variables or confounders that are causally related.
Causal Discovery with Multi-Domain LiNGAM for Latent Factors
In this paper, we propose Multi-Domain Linear Non-Gaussian Acyclic Models for Latent Factors (MD-LiNA), where the causal structure among latent factors of interest is shared for all domains, and we provide its identification results.
TAG : Type Auxiliary Guiding for Code Comment Generation
Existing leading code comment generation approaches with the structure-to-sequence framework ignores the type information of the interpretation of the code, e. g., operator, string, etc.
Triad Constraints for Learning Causal Structure of Latent Variables
In this paper, by properly leveraging the non-Gaussianity of the data, we propose to estimate the structure over latent variables with the so-called Triad constraints: we design a form of "pseudo-residual" from three variables, and show that when causal relations are linear and noise terms are non-Gaussian, the causal direction between the latent variables for the three observed variables is identifiable by checking a certain kind of independence relationship.
Disentanglement Challenge: From Regularization to Reconstruction
The challenge of learning disentangled representation has recently attracted much attention and boils down to a competition using a new real world disentanglement dataset (Gondal et al., 2019).
Causal Mechanism Transfer Network for Time Series Domain Adaptation in Mechanical Systems
However, the mainstream domain adaptation methods cannot achieve ideal performance on time series data, because most of them focus on static samples and even the existing time series domain adaptation methods ignore the properties of time series data, such as temporal causal mechanism.
Causal Discovery with Cascade Nonlinear Additive Noise Models
In this work, we propose a cascade nonlinear additive noise model to represent such causal influences--each direct causal relation follows the nonlinear additive noise model but we observe only the initial cause and final effect.
Causal Discovery from Discrete Data using Hidden Compact Representation
In this paper we make an attempt to find a way to solve this problem by assuming a two-stage causal process: the first stage maps the cause to a hidden variable of a lower cardinality, and the second stage generates the effect from the hidden representation.
An Encoder-Decoder Framework Translating Natural Language to Database Queries
These techniques help the neural network better focus on understanding semantics of operations in natural language and save the efforts on SQL grammar learning.
SADA: A General Framework to Support Robust Causation Discovery with Theoretical Guarantee
We theoretically prove that SADA always reduces the scales of problems without sacrifice on accuracy, under the condition of local causal sparsity and reliable conditional independence tests.
Component-Based Distributed Framework for Coherent and Real-Time Video Dehazing
Traditional dehazing techniques, as a well studied topic in image processing, are now widely used to eliminate the haze effects from individual images.
