Cat P. Le

Cat P. Le, Luke Dai, Michael Johnston et al.

Effective evaluation methods remain a significant challenge for research on open-domain conversational dialogue systems. Explicit satisfaction ratings can be elicited from users, but users often do not provide ratings when asked, and those they give can be highly subjective. Post-hoc ratings by experts are an alternative, but these can be both expensive and complex to collect. Here, we explore the creation of automated methods for predicting both expert and user ratings of open-domain dialogues. We compare four different approaches. First, we train a baseline model using an end-to-end transformer to predict ratings directly from the raw dialogue text. The other three methods are variants of a two-stage approach in which we first extract interpretable features at the turn level that capture, among other aspects, user dialogue behaviors indicating contradiction, repetition, disinterest, compliments, or criticism. We project these features to the dialogue level and train a dialogue-level MLP regression model, a dialogue-level LSTM, and a novel causal inference model called counterfactual-LSTM (CF-LSTM) to predict ratings. The proposed CF-LSTM is a sequential model over turn-level features which predicts ratings using multiple regressors depending on hypotheses derived from the turn-level features. As a causal inference model, CF-LSTM aims to learn the underlying causes of a specific event, such as a low rating. We also bin the user ratings and perform classification experiments with all four models. In evaluation experiments on conversational data from the Alexa Prize SocialBot, we show that the CF-LSTM achieves the best performance for predicting dialogue ratings and classification.

Ahmed Aloui, Juncheng Dong, Cat P. Le et al.

This work considers the problem of transferring causal knowledge between tasks for Individual Treatment Effect (ITE) estimation. To this end, we theoretically assess the feasibility of transferring ITE knowledge and present a practical framework for efficient transfer. A lower bound is introduced on the ITE error of the target task to demonstrate that ITE knowledge transfer is challenging due to the absence of counterfactual information. Nevertheless, we establish generalization upper bounds on the counterfactual loss and ITE error of the target task, demonstrating the feasibility of ITE knowledge transfer. Subsequently, we introduce a framework with a new Causal Inference Task Affinity (CITA) measure for ITE knowledge transfer. Specifically, we use CITA to find the closest source task to the target task and utilize it for ITE knowledge transfer. Empirical studies are provided, demonstrating the efficacy of the proposed method. We observe that ITE knowledge transfer can significantly (up to 95%) reduce the amount of data required for ITE estimation.

Cat P. Le, Chris Cannella, Ali Hasan et al.

Transformers have demonstrated remarkable efficacy in forecasting time series data. However, their extensive dependence on self-attention mechanisms demands significant computational resources, thereby limiting their practical applicability across diverse tasks, especially in multimodal problems. In this work, we propose a new architecture, called perceiver-CDF, for modeling cumulative distribution functions (CDF) of time series data. Our approach combines the perceiver architecture with a copula-based attention mechanism tailored for multimodal time series prediction. By leveraging the perceiver, our model efficiently transforms high-dimensional and multimodal data into a compact latent space, thereby significantly reducing computational demands. Subsequently, we implement a copula-based attention mechanism to construct the joint distribution of missing data for prediction. Further, we propose an output variance testing mechanism to effectively mitigate error propagation during prediction. To enhance efficiency and reduce complexity, we introduce midpoint inference for the local attention mechanism. This enables the model to efficiently capture dependencies within nearby imputed samples without considering all previous samples. The experiments on the unimodal and multimodal benchmarks consistently demonstrate a 20% improvement over state-of-the-art methods while utilizing less than half of the computational resources.

Ahmed Aloui, Juncheng Dong, Cat P. Le et al.

One of the most significant challenges in Conditional Average Treatment Effect (CATE) estimation is the statistical discrepancy between distinct treatment groups. To address this issue, we propose a model-agnostic data augmentation method for CATE estimation. First, we derive regret bounds for general data augmentation methods suggesting that a small imputation error may be necessary for accurate CATE estimation. Inspired by this idea, we propose a contrastive learning approach that reliably imputes missing potential outcomes for a selected subset of individuals formed using a similarity measure. We augment the original dataset with these reliable imputations to reduce the discrepancy between different treatment groups while inducing minimal imputation error. The augmented dataset can subsequently be employed to train standard CATE estimation models. We provide both theoretical guarantees and extensive numerical studies demonstrating the effectiveness of our approach in improving the accuracy and robustness of numerous CATE estimation models.

Jianyu Wang, Jacob Nean-Hua Sheikh, Cat P. Le et al.

Lifelong deep learning (LDL) trains neural networks to learn sequentially across tasks while preserving prior knowledge. We propose Task-Aware Multi-Expert (TAME), a continual learning algorithm that leverages task similarity to guide expert selection and knowledge transfer. TAME maintains a pool of pretrained neural networks and activates the most relevant expert for each new task. A shared dense layer integrates features from the chosen expert to generate predictions. To reduce catastrophic forgetting, TAME uses a replay buffer that stores representative samples and embeddings from previous tasks and reuses them during training. An attention mechanism further prioritizes the most relevant stored information for each prediction. Together, these components allow TAME to adapt flexibly while retaining important knowledge across evolving task sequences. Experiments on binary classification tasks derived from CIFAR-100 show that TAME improves accuracy on new tasks while sustaining performance on earlier ones, highlighting its effectiveness in balancing adaptation and retention in lifelong learning settings.

Cat P. Le, Juncheng Dong, Ahmed Aloui et al.

The main challenge in continual learning for generative models is to effectively learn new target modes with limited samples while preserving previously learned ones. To this end, we introduce a new continual learning approach for conditional generative adversarial networks by leveraging a mode-affinity score specifically designed for generative modeling. First, the generator produces samples of existing modes for subsequent replay. The discriminator is then used to compute the mode similarity measure, which identifies a set of closest existing modes to the target. Subsequently, a label for the target mode is generated and given as a weighted average of the labels within this set. We extend the continual learning model by training it on the target data with the newly-generated label, while performing memory replay to mitigate the risk of catastrophic forgetting. Experimental results on benchmark datasets demonstrate the gains of our continual learning approach over the state-of-the-art methods, even when using fewer training samples.

Cat P. Le, Juncheng Dong, Mohammadreza Soltani et al.

We propose an asymmetric affinity score for representing the complexity of utilizing the knowledge of one task for learning another one. Our method is based on the maximum bipartite matching algorithm and utilizes the Fisher Information matrix. We provide theoretical analyses demonstrating that the proposed score is mathematically well-defined, and subsequently use the affinity score to propose a novel algorithm for the few-shot learning problem. In particular, using this score, we find relevant training data labels to the test data and leverage the discovered relevant data for episodically fine-tuning a few-shot model. Results on various few-shot benchmark datasets demonstrate the efficacy of the proposed approach by improving the classification accuracy over the state-of-the-art methods even when using smaller models.

Cat P. Le, Mohammadreza Soltani, Juncheng Dong et al.

We formulate an asymmetric (or non-commutative) distance between tasks based on Fisher Information Matrices, called Fisher task distance. This distance represents the complexity of transferring the knowledge from one task to another. We provide a proof of consistency for our distance through theorems and experiments on various classification tasks from MNIST, CIFAR-10, CIFAR-100, ImageNet, and Taskonomy datasets. Next, we construct an online neural architecture search framework using the Fisher task distance, in which we have access to the past learned tasks. By using the Fisher task distance, we can identify the closest learned tasks to the target task, and utilize the knowledge learned from these related tasks for the target task. Here, we show how the proposed distance between a target task and a set of learned tasks can be used to reduce the neural architecture search space for the target task. The complexity reduction in search space for task-specific architectures is achieved by building on the optimized architectures for similar tasks instead of doing a full search and without using this side information. Experimental results for tasks in MNIST, CIFAR-10, CIFAR-100, ImageNet datasets demonstrate the efficacy of the proposed approach and its improvements, in terms of the performance and the number of parameters, over other gradient-based search methods, such as ENAS, DARTS, PC-DARTS.

Cat P. Le, Mohammadreza Soltani, Robert Ravier et al.

In this paper, we propose a neural architecture search framework based on a similarity measure between some baseline tasks and a target task. We first define the notion of the task similarity based on the log-determinant of the Fisher Information matrix. Next, we compute the task similarity from each of the baseline tasks to the target task. By utilizing the relation between a target and a set of learned baseline tasks, the search space of architectures for the target task can be significantly reduced, making the discovery of the best candidates in the set of possible architectures tractable and efficient, in terms of GPU days. This method eliminates the requirement for training the networks from scratch for a given target task as well as introducing the bias in the initialization of the search space from the human domain.

Cat P. Le, Mohammadreza Soltani, Robert Ravier et al.

The design of handcrafted neural networks requires a lot of time and resources. Recent techniques in Neural Architecture Search (NAS) have proven to be competitive or better than traditional handcrafted design, although they require domain knowledge and have generally used limited search spaces. In this paper, we propose a novel framework for neural architecture search, utilizing a dictionary of models of base tasks and the similarity between the target task and the atoms of the dictionary; hence, generating an adaptive search space based on the base models of the dictionary. By introducing a gradient-based search algorithm, we can evaluate and discover the best architecture in the search space without fully training the networks. The experimental results show the efficacy of our proposed task-aware approach.

Cat P. Le, Yi Zhou, Jie Ding et al.

Classical supervised classification tasks search for a nonlinear mapping that maps each encoded feature directly to a probability mass over the labels. Such a learning framework typically lacks the intuition that encoded features from the same class tend to be similar and thus has little interpretability for the learned features. In this paper, we propose a novel supervised learning model named Supervised-Encoding Quantizer (SEQ). The SEQ applies a quantizer to cluster and classify the encoded features. We found that the quantizer provides an interpretable graph where each cluster in the graph represents a class of data samples that have a particular style. We also trained a decoder that can decode convex combinations of the encoded features from similar and different clusters and provide guidance on style transfer between sub-classes.