United States

Machine learning techniques are notably vulnerable to natural or adversarial perturbations, which can lead to catastrophic failures with significant economic, ethical, and societal risks. In this New Faculty Highlight Talk, I will showcase my research on harnessing robust statistics to build robust and trustworthy AI systems. Specifically, I will highlight my research breakthroughs in graph learning (GNNs), large language models (LLMs), deep equilibrium models (DEQs), and general deep representation learning. These breakthroughs stem from a unified and principled robust statistics framework that incorporates robustness as the core inductive bias in deep learning architecture. This approach has enabled significant improvements in intrinsic robustness and generalization, even in complex and challenging environments. My research demonstrates the transformative potential of harnessing robust statistics in enhancing the robustness and trustworthiness of AI systems. Looking forward, I will continue to push this frontier by advocating the design of robustness-informed neural networks across various areas.

AAAI 2025

Harnessing Robust Statistics for Trustworthy AI

We are pleased to announce the Thirty-Eighth AAAI Conference on Artificial Intelligence (AAAI-24), which will be held in Vancouver, British Columbia at the Vancouver Convention Centre – West Building from 20-27 February, 2024.

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-24 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and a range of other activities to be announced.

We expect for AAAI-24 to be an in-person conference – one author of all accepted papers will be expected to present work in person unless there are exceptional circumstances that prevent this.

In order to access the AAAI-24 event page you need to register [here](https://aaai.org/aaai-conference/registration/)

AAAI 2024

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. 

technical paper

We are pleased to announce the Thirty-Ninth AAAI Conference on Artificial Intelligence (AAAI-25), which will be held in Philadelphia, Pennsylvania at the Pennsylvania Convention Center from February 25 to March 4, 2025.

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-25 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and a range of other activities to be announced.

### [Invited Speakers](https://aaai.org/conference/aaai/aaai-25/aaai-25-invited-speakers/)

Register [here](https://aaai.org/conference/aaai/aaai-25/registration/)

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-25 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and a range of other activities to be announced.



The metro flow in Urban Rail Transit Systems (URTS) differs from other urban traffic flows because it is characterized by: (1) highly predetermined scheduling; and (2) interactively dynamic dependencies over the fixed physical infrastructure that vary with spatiotemporal and environmental factors. Notwithstanding the advances in graph neural networks, existing efforts fail to fully capture the characteristics and complex spatiotemporal dynamics specific to metro flow, as the innate graph-aware interactions underlying a metro flow are frequently affected by an amalgamation of: intrinsic connectivity, environmental associations, and flow-activated correlation, which usually dynamically evolve over time while containing redundant signals. We propose $\textbf{ReDyNet}$, a novel $\textbf{Re}$sponsive $\textbf{Dy}$namic Graph Neural $\textbf{Net}$work to accurately understand the spatiotemporal dynamics of metro flow and external factors. Specifically, it employs a responsive mechanism that adapts to variations in metro flow and external influences, ensuring the construction of an appropriate dynamic graph. In addition, ReDyNet follows the merits of information bottleneck (IB) theory with redundancy disentanglement to enhance the clarity and precision of contextual spatial signals. Our experiments conducted on three real-world metro passenger flow datasets demonstrate that the proposed ReDyNet outperforms several representative baselines.

Responsive Dynamic Graph Disentanglement for Metro Flow Forecasting

This paper presents fast and exact methods for computing the probability of acceptance of an argument using Dung's semantics in the Constellation paradigm of Abstract Argumentation. 
For (directed) Singly-Connected Graphs (SCGs), the problem can now be solved in linearithmic time instead of being exponential in the number of attacks, as reported in the literature.  
Moreover, in the more general case of (directed) Acyclic Graphs (AGs), we provide an algorithm whose time complexity is linearithmic in the product of the out-degree of dependent arguments, i.e., arguments reaching the argument considered for acceptance through multiple paths in the graph. 
We theoretically show that this complexity is lower than the lower-bound of the (exact) Constellation method, which is also supported by empirical results. 
We also compare our approach on AGs with the (approximate) Monte-Carlo method, which is stopped when our approach obtains the exact results. Within this time constraint, Monte-Carlo still outputs significant errors, underlying the fast computation of our approach.

Fast Computing of Dung Semantics in Acyclic Probabilistic Argumentation Frameworks

Decision-focused learning (DFL) offers an end-to-end approach to the predict-then-optimize (PO) framework by training predictive models directly on decision loss (DL), enhancing decision-making performance within PO contexts.
However, the implementation of DFL poses distinct challenges. Primarily, the decision loss can result in deviation from the physical significance of the predictions under limited data. Additionally, some prediction models are non-differentiable or black-box, which cannot be adjusted using gradient-based methods.

To tackle those challenges, we propose a novel framework, Decision-Focused Fine-tuning (DFF), which embeds the DFL module into the PO pipeline via a novel bias correction module. DFF is formulated as a constrained optimization problem that maintains the proximity of the DL-enhanced model to the original prediction model within a defined trust region. We theoretically prove that DFF strictly confines prediction bias within a predetermined upper bound, even with limited datasets, thereby substantially reducing prediction shifts caused by DL under limited data. Furthermore, the bias correction module can be integrated into diverse prediction models, enhancing adaptability to a broad range of PO tasks. Extensive evaluations on synthetic and real-world datasets, including network flow, portfolio optimization, and resource allocation problems with different prediction models, demonstrate that DFF not only improves decision performance but also adheres to fine-tuning constraints, showcasing robust adaptability across various scenarios.

DFF: Decision-Focused Fine-Tuning for Smarter Predict-Then-Optimize with Limited Data

Even though data annotation is extremely important for interpretability, research, and development of artificial intelligence solutions, annotating data remains costly. Research efforts such as active learning or few-shot learning alleviate the cost by increasing sample efficiency, yet the problem of annotating data more quickly has received comparatively little attention. Leveraging a predictor has been shown to reduce annotation cost in practice but has not been theoretically considered. We ask the following question: to annotate a binary classification dataset with $N$ samples, can the annotator answer less than $N$ yes/no questions? Framing this question-and-answer (Q\&A) game as an optimal encoding problem, we find a positive answer given by the Huffman encoding of the possible labelings. Unfortunately, the algorithm is computationally intractable even for small dataset sizes. As a practical method, we propose to minimize a cost function a few steps ahead, similarly to lookahead minimization in optimal control. This solution is analyzed, compared with the optimal one, and evaluated using several synthetic and real-world datasets. The method allows a significant improvement ($23-86\%$) in the annotation efficiency of real-world datasets.

Optimal and Efficient Binary Questioning for Accelerated Annotation

Group Equivariant Convolution (GConv) can effectively handle rotational symmetry data.
They assume uniform and strict rotational symmetry across all features, as the transformations under the specific group. 
However, real-world data rarely conforms to strict rotational symmetry commonly referred to as Rotational Symmetry-Breaking in the system or dataset, making GConv unable to adapt effectively to this phenomenon. 
Motivated by this, we propose a simple but highly effective method to address this problem, which utilizes a set of learnable biases called the $G$-Biases under the group order to break strict group constraints and achieve $\textbf{R}$elaxed $\textbf{R}$otational $\textbf{E}$quivarant $\textbf{Conv}$olution (RREConv). 
We conduct extensive experiments to validate Relaxed Rotational Equivariance on rotational symmetry groups $\mathcal{C}_n$ (e.g. $\mathcal{C}_2$, $\mathcal{C}_4$, and $\mathcal{C}_6$ groups). 
Further experiments demonstrate that our proposed RREConv-based methods achieve excellent performance, compared to existing GConv-based methods in classification and detection tasks on natural image datasets.

Relaxed Rotational Equivariance via G-Biases in Vision

Graph neural networks (GNNs) have emerged as an effective tool for fraud detection, identifying fraudulent users, and uncovering malicious behaviors. However, attacks against GNN-based fraud detectors and their risks have rarely been studied, thereby leaving potential threats unaddressed. Recent findings suggest that frauds are increasingly organized as gangs or groups. In this work, we design attack scenarios where fraud gangs aim to make their fraud nodes misclassified as benign by camouflaging their illicit activities in collusion. Based on these scenarios, we study adversarial attacks against GNN-based fraud detectors by simulating attacks of fraud gangs in three real-world fraud cases: spam reviews, fake news, and medical insurance frauds. We define these attacks as multi-target graph injection attacks and propose MonTi, a transformer-based Multi-target one-Time graph injection attack model. MonTi simultaneously generates attributes and edges of all attack nodes with a transformer encoder, capturing interdependencies between attributes and edges more effectively than most existing graph injection attack methods that generate these elements sequentially. Additionally, MonTi adaptively allocates the degree budget for each attack node to explore diverse injection structures involving target, candidate, and attack nodes, unlike existing methods that fix the degree budget across all attack nodes. Experiments show that MonTi outperforms the state-of-the-art graph injection attack methods on five real-world graphs.

Unveiling the Threat of Fraud Gangs to Graph Neural Networks: Multi-Target Graph Injection Attacks Against GNN-Based Fraud Detectors

The generalization problem is broadly recognized as a critical challenge in detecting deepfakes. Most previous work believes that the generalization gap is caused by the differences among various forgery methods. However, our investigation reveals that the generalization issue can still occur even when the forgery techniques are identical or similar. In this work, we identify two biases that detectors may also be prone to overfitting: position bias and content bias, as depicted in Fig. 1. For the position bias, we observe that detectors are prone to ``lazily" depending on the specific positions within an image (e.g., central regions even no forgery). As for content bias, we argue that detectors may potentially and mistakenly utilize forgery-unrelated information for detection (e.g., background and hair). To intervene in these biases, we propose two branches for shuffling and mixing with tokens in the latent space of transformers. For the shuffling branch, we rearrange the tokens and corresponding position embedding for each image while maintaining the local correlation. For the mixing branch, we randomly select and mix the tokens in the latent space between two images with the same label within the mini-batch to recombine the content information. During the learning process, we align the outputs of detectors from different branches in both feature space and logit space. Contrastive losses for features and divergence losses for logits are applied to obtain unbiased feature representation and classifiers. We demonstrate and verify the effectiveness of our method through extensive experiments on widely used evaluation datasets.

Exploring Unbiased Deepfake Detection via Token-Level Shuffling and Mixing

The domain of non-line-of-sight (NLOS) imaging is advancing rapidly, offering the capability to reveal occluded scenes that are not directly visible. However, contemporary NLOS systems are confronted with several significant challenges: (1) The computational and storage requirements are profound due to the inherent three-dimensional grid data structure, impeding practical application. (2) The simultaneous reconstruction of albedo and depth information requires a delicate balance using hyper-parameters in the loss function, rendering the concurrent reconstruction of texture and depth information difficult. This paper introduces an innovative methodology to overcome these obstacles. The proposed technique, DG-NLOS, integrates two branches: an albedo-focused reconstruction branch dedicated to the recovery of albedo information, and a depth-focused reconstruction branch that extracts geometrical details. The dual-branch framework segregates content delivery to the respective reconstructions, thereby enhancing the quality of the retrieved data. Moreover, we employ the graph as a fundamental component to transform dense NLOS grid data into sparse structural features for efficient reconstruction. In essence, DG-NLOS demonstrates robustness in realistic scenarios by adeptly handling various types of corruption in NLOS reconstruction tasks, including different noise levels, multiple blur kernels, and variations in temporal resolution. The code will be made available.

Dual-branch Graph Feature Learning for NLOS Imaging

Transfer learning aims to transfer knowledge or information from a source domain to a relevant target domain. It involves two key challenges: distribution shifts and trustworthiness concerns. Having these challenges in mind, my research focuses on understanding transfer learning from the perspective of knowledge transferability (e.g., IID and non-IID learning tasks) and trustworthiness (e.g., adversarial robustness, data privacy, and performance fairness).

Towards Trustworthy Machine Learning Under Distribution Shifts

Along with the broad deployment of deep learning (DL) systems, their lack of trustworthiness, such as their lack of robustness, fairness, and numerical reliability, is raising serious social concerns, especially in safety-critical scenarios such as autonomous driving and aircraft navigation. Hence, a rigorous and accurate evaluation of the trustworthiness of DL systems is essential and would be a prerequisite for improving DL trustworthiness. The first part of the talk will be an overview of certified methods for DL trustworthiness. These methods provide computable guarantees for DL systems in terms of worst-case trustworthiness under certain realistic conditions, such as the accuracy lower bound against arbitrary tiny perturbations. Based on our taxonomy and systematization, we illustrate key methodologies, specifically semantic randomized smoothing and branch-and-bound, and their implications for certified DL trustworthiness.

As a representative of recent DL breakthroughs, large language models (LLMs) are transforming our lives, but, on the other hand, posing more challenges to trustworthiness. For example, LLMs can be jailbroken with adversarial prompts to output harmful content with bias, harassment, misinformation, and more. The second part of the talk will be an overview of LLM trustworthiness. We will start with sharing hands-on experience in developing fontier LLMs, then illustrate common LLM trustworthiness issues via examples, then demonstrate evaluation challenges, take one benchmark as an example, and conclude by envisioning certifiable trustworthiness for LLMs.

Downloads

Next from AAAI 2025

Responsive Dynamic Graph Disentanglement for Metro Flow Forecasting

Similar lecture

Towards Trustworthy Deep Learning | VIDEO

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from AAAI 2025

Responsive Dynamic Graph Disentanglement for Metro Flow Forecasting

Similar lecture

Towards Trustworthy Deep Learning | VIDEO

Downloads