We agree with your assessment.

A trivial method for satisfying FTU fairness, is to remove the protected attribute from downstream learners. We first provide a motivating example explaining why this is sub-optimal. We then follow this with an experiment on the Adult dataset. A.1 Example Defining fairness is task and data dependent. For example, let us assume two datasets are generated by the graphical models in Figure 1. Data generated by the top graph is considered fair: Education affects past experience (Resume), which together affect future job prospects (Job).

Machine learning models have been criticized for reflecting unfair biases in the training data. Instead of solving for this by introducing fair learning algorithms directly, we focus on generating fair synthetic data, such that any downstream learner is fair. Generating fair synthetic data from unfair data-- while remaining truthful to the underlying data-generating process (DGP) --is non-trivial. In this paper, we introduce DECAF: a GAN-based fair synthetic data generator for tabular data. With DECAF we embed the DGP explicitly as a structural causal model in the input layers of the generator, allowing each variable to be reconstructed conditioned on its causal parents. This procedure enables inference-time debiasing, where biased edges can be strategically removed for satisfying user-defined fairness requirements. The DECAF framework is versatile and compatible with several popular definitions of fairness. In our experiments, we show that DECAF successfully removes undesired bias and-- in contrast to existing methods --is capable of generating high-quality synthetic data. Furthermore, we provide theoretical guarantees on the generator's convergence and the fairness of downstream models.

Benefiting from the booming deep learning techniques, neural operators (NO) are considered as an ideal alternative to break the traditions of solving Partial Differential Equations (PDE) with expensive cost.

Optical flow estimation is a classical yet challenging task in computer vision. One of the essential factors in accurately predicting optical flow is to alleviate occlusions between frames. However, it is still a thorny problem for current top-performing optical flow estimation methods due to insufficient local evidence to model occluded areas. In this paper, we propose the Super Kernel Flow Network (SKFlow), a CNN architecture to ameliorate the impacts of occlusions on optical flow estimation. SKFlow benefits from the super kernels which bring enlarged receptive fields to complement the absent matching information and recover the occluded motions.

Nine image pairs are generated by personalized text-to-image models, each of which is fine-tuned on a respective, single style reference image displayed at the corner of the left image of each pair. Fine-grained concepts are written on top of the images for comparisons, showing the nuanced compositionality encompassing color, foreground object, background, and textures. Full prompts are available in Appendix A.1.

We present the full grammar of the Karel language in Figure 1. To represent the execution states, each Karel grid world has a maximum size of 18 18, and each cell in the grid world is represented by a 16-dimensional vector corresponding to the features in Table 5. Therefore, each grid world is represented as a 16 18 18 tensor. B.1 Program Decoder Our model follows the encoder-decoder framework in prior work on neural program synthesis from input-output examples [17, 9], which includes an encoder for the input-output pairs, and a decoder to synthesize the program. For C program synthesis, our input-output encoder architecture is similar to RobustFill [17].

Program synthesis from input-output (IO) examples has been a long-standing challenge. While recent works demonstrated limited success on domain-specific languages (DSL), it remains highly challenging to apply them to real-world programming languages, such as C. Due to complicated syntax and token variation, there are three major challenges: (1) unlike many DSLs, programs in languages like C need to compile first and are not executed via interpreters; (2) the program search space grows exponentially when the syntax and semantics of the programming language become more complex; and (3) collecting a large-scale dataset of real-world programs is non-trivial. As a first step to address these challenges, we propose LaSynth and show its efficacy in a restricted-C domain (i.e., C code with tens of tokens, with sequential, branching, loop and simple arithmetic operations but no library call). More specifically, LaSynth learns the latent representation to approximate the execution of partially generated programs, even if they are incomplete in syntax (addressing (1)). The learned execution significantly improves the performance of next token prediction over existing approaches, facilitating search (addressing (2)). Finally, once trained with randomly generated groundtruth programs and their IO pairs, LaSynth can synthesize more concise programs that resemble human-written code. Furthermore, retraining our model with these synthesized programs yields better performance with fewer samples for both Karel and C program synthesis, indicating the promise of leveraging the learned program synthesizer to improve the dataset quality for input-output program synthesis (addressing (3)). When evaluating on whether the program execution outputs match the IO pairs, LaSynth achieves 55.2% accuracy on generating simple C code with tens of tokens including loops and branches, outperforming existing approaches without executors by around 20%.