See-Kiong Ng

AAMAS Conference 2026 Conference Paper

Incentivizing Black-Box Model Sharing with Fair Rewards and Payoffs

• Wenyang Hu
• Xinyi Xu
• See-Kiong Ng
• Bryan Kian Hsiang Low

Black-box model sharing allows multiple parties to build a highquality ensemble model without revealing private information. However, self-interested parties require incentives, specifically Fairness and Individual Rationality, to contribute their predictions. Existing mechanisms typically handle either monetary payoffs or data rewards in isolation, failing to address scenarios where parties have varyingbudgetsanddataneeds. Weproposeanovelincentivemechanism that fairly distributes ensemble predictions and monetary payoffs commensurate with each agent’s contribution. Specifically, we use the average ensemble weight for the contribution measure and derive a closed-form solution that explicitly determines the fair reward and payoff allocation given the contribution and payment.

EAAI Journal 2026 Journal Article

Large language models for explainable fault diagnosis of machines

• Hamzah A.A.M. Qaid
• Bo Zhang
• Shuai Su
• Dan Li
• See-Kiong Ng
• Wei Li

Large Language Models (LLMs) have demonstrated remarkable capabilities in capturing complex conceptual representations from textual data for a wide range of real-world applications. However, in Intelligent Fault Diagnosis (IFD), leveraging sensor data such as vibration signals is essential but remains a challenge due to the modality gap between time series and LLMs’ inputs. Existing efforts to bridge this gap often treat LLMs merely as classifiers, overlooking their potential for understanding and reasoning over vibration-based data. In this paper, we propose a novel LLM-based fault diagnosis framework (FD-LLM) that aligns vibration signals with LLMs by encoding the signals into textual representations. FD-LLM introduces a classification-oriented approach, which formulates fault diagnosis as a multi-class classification task for benchmarking LLMs’ performance, and a context-aware spectrum language modeling approach that enables explainable, reasoning-driven fault analysis. We evaluate four open-source LLMs using FD-LLM across multiple datasets and noise conditions, assessing their validity, adaptability, and robustness. The results demonstrate that models such as LLaMA models achieve robust diagnostic performance, strong zero-shot adaptability across operating conditions, and effective generalization in cross-dataset scenarios with few-shot learning. The results further indicate that explainable fault diagnosis can be achieved in LLMs.

NeurIPS Conference 2025 Conference Paper

Afterburner: Reinforcement Learning Facilitates Self-Improving Code Efficiency Optimization

• Mingzhe Du
• Anh Tuan Luu
• Yue Liu
• Yuhao Qing
• Dong Huang
• Xinyi He
• Qian Liu
• Zejun Ma

Large Language Models (LLMs) generate functionally correct solutions but often fall short in code efficiency, a critical bottleneck for real-world deployment. In this paper, we introduce a novel test-time iterative optimization framework to address this, employing a closed-loop system where LLMs iteratively refine code based on empirical performance feedback from an execution sandbox. We explore three training strategies: Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and Group Relative Policy Optimization~(GRPO). Experiments on our Venus dataset and the APPS benchmark show that SFT and DPO rapidly saturate in efficiency gains. In contrast, GRPO, using reinforcement learning (RL) with execution feedback, continuously optimizes code performance, significantly boosting both pass@1 (from 47% to 62%) and the likelihood of outperforming human submissions in efficiency (from 31% to 45%). Our work demonstrates effective test-time code efficiency improvement and critically reveals the power of RL in teaching LLMs to truly self-improve code efficiency. We released our code and data at https: //github. com/Elfsong/Afterburner.

AAAI Conference 2025 Conference Paper

Aligning Large Language Models for Faithful Integrity Against Opposing Argument

• Yong Zhao
• Yang Deng
• See-Kiong Ng
• Tat-Seng Chua

Large Language Models (LLMs) have demonstrated impressive capabilities in complex reasoning tasks. However, they can be easily misled by unfaithful arguments during conversations, even when their original statements are correct. To this end, we investigate the problem of maintaining faithful integrity in LLMs. This involves ensuring that LLMs adhere to their faithful statements in the face of opposing arguments and are able to correct their incorrect statements when presented with faithful arguments. In this work, we propose a novel framework, named Alignment for Faithful Integrity with Confidence Estimation (AFICE), which aims to align the LLM responses with faithful integrity. Specifically, AFICE first designs a Bilateral Confidence Estimation (BCE) approach for estimating the uncertainty of each response generated by the LLM given a specific context, which simultaneously estimate the model's confidence to the question based on the internal states during decoding as well as to the answer based on cumulative probability ratios. With the BCE, we construct a conversational preference dataset composed of context, original statement, and argument, which is adopted for aligning the LLM for faithful integrity using Direct Preference Optimization (DPO). Extensive experimental results on a wide range of benchmarks demonstrate significant improvements in the LLM's ability to maintain faithful responses when encountering opposing arguments, ensuring both the practical utility and trustworthiness of LLMs in complex interactive settings.

ICLR Conference 2025 Conference Paper

CHiP: Cross-modal Hierarchical Direct Preference Optimization for Multimodal LLMs

• Jinlan Fu
• Shenzhen Huangfu
• Hao Fei 0001
• Xiaoyu Shen 0001
• Bryan Hooi
• Xipeng Qiu
• See-Kiong Ng

Multimodal Large Language Models (MLLMs) still struggle with hallucinations despite their impressive capabilities. Recent studies have attempted to mitigate this by applying Direct Preference Optimization (DPO) to multimodal scenarios using preference pairs from text-based responses. However, our analysis of representation distributions reveals that multimodal DPO struggles to align image and text representations and to distinguish between hallucinated and non-hallucinated descriptions. To address these challenges, In this work, we propose a Cross-modal Hierarchical Direct Preference Optimization (CHiP) to address these limitations. We introduce a visual preference optimization module within the DPO framework, enabling MLLMs to learn from both textual and visual preferences simultaneously. Furthermore, we propose a hierarchical textual preference optimization module that allows the model to capture preferences at multiple granular levels, including response, segment, and token levels. We evaluate CHiP through both quantitative and qualitative analyses, with results across multiple benchmarks demonstrating its effectiveness in reducing hallucinations. On the Object HalBench dataset, CHiP outperforms DPO in hallucination reduction, achieving improvements of 52.7% and 55.5% relative points based on the base model Muffin and LLaVA models, respectively. We make all our datasets and code publicly available.

ICLR Conference 2025 Conference Paper

Confidence Elicitation: A New Attack Vector for Large Language Models

• Brian Formento
• Chuan-Sheng Foo
• See-Kiong Ng

A fundamental issue in deep learning has been adversarial robustness. As these systems have scaled, such issues have persisted. Currently, large language models (LLMs) with billions of parameters suffer from adversarial attacks just like their earlier, smaller counterparts. However, the threat models have changed. Previously, having gray-box access, where input embeddings or output logits/probabilities were visible to the user, might have been reasonable. However, with the introduction of closed-source models, no information about the model is available apart from the generated output. This means that current black-box attacks can only utilize the final prediction to detect if an attack is successful. In this work, we investigate and demonstrate the potential of attack guidance, akin to using output probabilities, while having only black-box access in a classification setting. This is achieved through the ability to elicit confidence from the model. We empirically show that the elicited confidence is calibrated and not hallucinated for current LLMs. By minimizing the elicited confidence, we can therefore increase the likelihood of misclassification. Our new proposed paradigm demonstrates promising state-of-the-art results on three datasets across two models (LLaMA-3-8B-Instruct and Mistral-7B-Instruct-V0.3) when comparing our technique to existing hard-label black-box attack methods that introduce word-level substitutions. The code is publicly available at GitHub: Confidence_Elicitation_Attacks.

NeurIPS Conference 2025 Conference Paper

Continual Multimodal Contrastive Learning

• Xiaohao Liu
• Xiaobo Xia
• See-Kiong Ng
• Tat-Seng Chua

Multimodal Contrastive Learning (MCL) advances in aligning different modalities and generating multimodal representations in a joint space. By leveraging contrastive learning across diverse modalities, large-scale multimodal data enhances representational quality. However, a critical yet often overlooked challenge remains: multimodal data is rarely collected in a single process, and training from scratch is computationally expensive. Instead, emergent multimodal data can be used to optimize existing models gradually, \textit{i. e. }, models are trained on a sequence of modality pair data. We define this problem as Continual Multimodal Contrastive Learning (CMCL), an underexplored yet crucial research direction at the intersection of multimodal and continual learning. In this paper, we formulate CMCL through two specialized principles of stability and plasticity. We theoretically derive a novel optimization-based method, which projects updated gradients from dual sides onto subspaces where any gradient is prevented from interfering with the previously learned knowledge. Two upper bounds provide theoretical insights on both stability and plasticity in our solution. Beyond our theoretical contributions, we conduct experiments on multiple datasets by comparing our method against advanced continual learning baselines. The empirical results further support our claims and demonstrate the efficacy of our method. Our codes are available at https: //github. com/Xiaohao-Liu/CMCL.

AAMAS Conference 2025 Conference Paper

DUPRE: Data Utility Prediction for Efficient Data Valuation

• Kieu Thao Nguyen Nguyen
• Rachael Hwee Ling Sim
• Quoc Phong Nguyen
• See-Kiong Ng
• Bryan Kian Hsiang Low

Data valuation is increasingly used in machine learning (ML) to decide the fair compensation for data owners and identify valuable or harmful data for improving ML models. Cooperative game theory-based data valuation, such as Data Shapley, requires evaluating the data utility (e. g. , validation accuracy) and retraining the ML model for multiple data subsets. While most existing works on efficient estimation of the Shapley values have focused on reducing the number of subsets to evaluate, our framework, DUPRE, takes an alternative yet complementary approach that reduces the cost per subset evaluation by predicting data utilities instead of evaluating them by model retraining. Specifically, given the evaluated data utilities of some data subsets, DUPRE fits a Gaussian process (GP) regression model to predict the utility of every other data subset. Our key contribution lies in the design of our GP kernel based on the sliced Wasserstein distance between empirical data distributions. In particular, we show that the kernel is valid and positive semidefinite, encodes prior knowledge of similarities between different data subsets, and can be efficiently computed. We empirically verify that DUPRE introduces low prediction error and speeds up data valuation for various ML models, datasets, and utility functions.

NeurIPS Conference 2025 Conference Paper

EffiBench-X: A Multi-Language Benchmark for Measuring Efficiency of LLM-Generated Code

• Yuhao Qing
• Boyu Zhu
• Mingzhe Du
• Zhijiang Guo
• Terry Yue Zhuo
• Qianru Zhang
• Jie Zhang
• Heming Cui

Existing code generation benchmarks primarily evaluate functional correctness, with limited attention to code efficiency, and they are often restricted to a single language such as Python. To address this gap, we introduce EffiBench‑X, the first large‑scale multi‑language benchmark specifically designed for robust efficiency evaluation of LLM‑generated code. EffiBench‑X supports Python, C++, Java, JavaScript, Ruby, and Go, and comprises competitive programming tasks paired with human‑expert solutions as efficiency baselines. Evaluating state‑of‑the‑art LLMs on EffiBench‑X reveals that while models frequently generate functionally correct code, they consistently underperform human experts in efficiency. Even the most efficient LLM‑generated solutions (e. g. , Qwen3‑32B) achieve only around 62% of human efficiency on average, with significant language‑specific variation: models tend to perform better in Python, Ruby, and JavaScript than in Java, C++, and Go (e. g. , DeepSeek‑R1’s Python code is markedly more efficient than its Java code). These findings highlight the need for research into optimization‑oriented methods to improve the efficiency of LLM‑generated code across diverse languages. The dataset and evaluation infrastructure are publicly available at https: //github. com/EffiBench/EffiBench-X. git and https: //huggingface. co/datasets/EffiBench/effibench-x.

ICLR Conference 2025 Conference Paper

Efficient Inference for Large Language Model-based Generative Recommendation

• Xinyu Lin 0001
• Chaoqun Yang 0002
• Wenjie Wang 0007
• Yongqi Li 0001
• Cunxiao Du
• Fuli Feng
• See-Kiong Ng
• Tat-Seng Chua

Large Language Model (LLM)-based generative recommendation has achieved notable success, yet its practical deployment is costly particularly due to excessive inference latency caused by autoregressive decoding. For lossless LLM decoding acceleration, Speculative Decoding (SD) has emerged as a promising solution. However, applying SD to generative recommendation presents unique challenges due to the requirement of generating top-K items (i.e., K distinct token sequences) as a recommendation list by beam search. This leads to more stringent verification in SD, where all the top-K sequences from the target LLM must be successfully drafted by the draft model at each decoding step. To alleviate this, we consider 1) boosting top-K sequence alignment between the draft model and the target LLM, and 2) relaxing the verification strategy to reduce trivial LLM calls. To this end, we propose an alignment framework named AtSpeed, which presents the AtSpeed-S optimization objective for top-K alignment under the strict top-K verification. Moreover, we introduce a relaxed sampling verification strategy that allows high-probability non-top-K drafted sequences to be accepted, significantly reducing LLM calls. Correspondingly, we propose AtSpeed-R for top-K alignment under this relaxed sampling verification. Empirical results on two real-world datasets demonstrate that AtSpeed significantly accelerates LLM-based generative recommendation, e.g., near 2x speedup under strict top-K verification and up to 2.5x speedup under relaxed sampling verification. The codes and datasets are available at~\url{https://github.com/Linxyhaha/AtSpeed}.

ICLR Conference 2025 Conference Paper

Efficient Top-m Data Values Identification for Data Selection

• Xiaoqiang Lin
• Xinyi Xu
• See-Kiong Ng
• Bryan Kian Hsiang Low

Data valuation has found many real-world applications, e.g., data pricing and data selection. However, the most adopted approach -- Shapley value (SV) -- is computationally expensive due to the large number of model trainings required. Fortunately, most applications (e.g., data selection) require only knowing the $m$ data points with the highest data values (i.e., top-$m$ data values), which implies the potential for fewer model trainings as exact data values are not required. Existing work formulates top-$m$ Shapley value identification as top-$m$ arms identification in multi-armed bandits (MAB). However, the proposed approach falls short because it does not utilize data features to predict data values, a method that has been shown empirically to be effective. A recent top-$m$ arms identification work does consider the use of arm features while assuming a linear relationship between arm features and rewards, which is often not satisfied in data valuation. To this end, we propose the GPGapE algorithm that uses the Gaussian process to model the \emph{non-linear} mapping from data features to data values, removing the linear assumption. We theoretically analyze the correctness and stopping iteration of GPGapE in finding an $(\epsilon, \delta)$-approximation to the top-$m$ data values. We further improve the computational efficiency, by calculating data values using small data subsets to reduce the computation cost of model training. We empirically demonstrate that GPGapE outperforms other baselines in top-$m$ data values identification, noisy data detection, and data subset selection on real-world datasets. We also demonstrate the efficiency of our GPGapE in data selection for large language model fine-tuning.

ICML Conference 2025 Conference Paper

Ferret: Federated Full-Parameter Tuning at Scale for Large Language Models

• Yao Shu
• Wenyang Hu
• See-Kiong Ng
• Bryan Kian Hsiang Low
• F. Richard Yu

Large Language Models (LLMs) have become indispensable in numerous real-world applications. However, fine-tuning these models at scale, especially in federated settings where data privacy and communication efficiency are critical, presents significant challenges. Existing approaches often resort to parameter-efficient fine-tuning (PEFT) to mitigate communication overhead, but this typically comes at the cost of model accuracy. To this end, we propose federated full-parameter tuning at scale for LLMs (Ferret), the first first-order method with shared randomness to enable scalable full-parameter tuning of LLMs across decentralized data sources while maintaining competitive model accuracy. Ferret accomplishes this through three aspects: (i) it employs widely used first-order methods for efficient local updates; (ii) it projects these updates into a low-dimensional space to considerably reduce communication overhead; and (iii) it reconstructs local updates from this low-dimensional space with shared randomness to facilitate effective full-parameter global aggregation, ensuring fast convergence and competitive final performance. Our rigorous theoretical analyses and insights along with extensive experiments, show that Ferret significantly enhances the scalability of existing federated full-parameter tuning approaches by achieving high computational efficiency, reduced communication overhead, and fast convergence, all while maintaining competitive model accuracy. Our implementation is available at https: //github. com/allen4747/Ferret.

NeurIPS Conference 2025 Conference Paper

L-MTP: Leap Multi-Token Prediction Beyond Adjacent Context for Large Language Models

• Xiaohao Liu
• Xiaobo Xia
• Weixiang Zhao
• Manyi Zhang
• Xianzhi Yu
• Xiu Su
• Shuo Yang
• See-Kiong Ng

Large language models (LLMs) have achieved notable progress. Despite their success, next-token prediction (NTP), the dominant method for LLM training and inference, is constrained in both contextual coverage and inference efficiency due to its inherently sequential process. To overcome these challenges, we propose leap multi-token prediction~(L-MTP), an innovative token prediction method that extends the capabilities of multi-token prediction (MTP) by introducing a leap-based mechanism. Unlike conventional MTP, which generates multiple tokens at adjacent positions, L-MTP strategically skips over intermediate tokens, predicting non-sequential ones in a single forward pass. This structured leap not only enhances the model's ability to capture long-range dependencies but also enables a decoding strategy specially optimized for non-sequential leap token generation, effectively accelerating inference. We theoretically demonstrate the benefit of L-MTP in improving inference efficiency. Experiments across diverse benchmarks validate its merit in boosting both LLM performance and inference speed. The source code is available at https: //github. com/Xiaohao-Liu/L-MTP.

ICML Conference 2025 Conference Paper

Leveraging Diffusion Model as Pseudo-Anomalous Graph Generator for Graph-Level Anomaly Detection

• Jinyu Cai
• Yunhe Zhang 0001
• Fusheng Liu
• See-Kiong Ng

A fundamental challenge in graph-level anomaly detection (GLAD) is the scarcity of anomalous graph data, as the training dataset typically contains only normal graphs or very few anomalies. This imbalance hinders the development of robust detection models. In this paper, we propose A nomalous G raph Diff usion (AGDiff), a framework that explores the potential of diffusion models in generating pseudo-anomalous graphs for GLAD. Unlike existing diffusion-based methods that focus on modeling data normality, AGDiff leverages the latent diffusion framework to incorporate subtle perturbations into graph representations, thereby generating pseudo-anomalous graphs that closely resemble normal ones. By jointly training a classifier to distinguish these generated graph anomalies from normal graphs, AGDiff learns more discriminative decision boundaries. The shift from solely modeling normality to explicitly generating and learning from pseudo graph anomalies enables AGDiff to effectively identify complex anomalous patterns that other approaches might overlook. Comprehensive experimental results demonstrate that the proposed AGDiff significantly outperforms several state-of-the-art GLAD baselines.

AAAI Conference 2025 Conference Paper

Mixture of Experts as Representation Learner for Deep Multi-View Clustering

• Yunhe Zhang
• Jinyu Cai
• Zhihao Wu
• Pengyang Wang
• See-Kiong Ng

Multi-view clustering (MVC) aims to integrate information from diverse data sources to facilitate the clustering process, which has achieved considerable success in various real-world applications. However, previous MVC methods typically employ one of two strategies: (1) designing separate feature extraction pipelines for each view, which restricts their ability to fully exploit collaborative potential; or (2) employing a single shared representation module, which hinders the capture of diverse, view-specific representations. To tackle these challenges, we introduce Deep Multi-View Clustering via Collaborative Experts (DMVC-CE), a novel MVC approach that employs the Mixture of Experts (MoE) framework. DMVC-CE incorporates a gating network that dynamically selects multiple experts for handling each data sample, capturing diverse and complementary information from different views. Additionally, to ensure balanced expert utilization and maintain their diversity, we introduce an equilibrium loss and a multi-expert distinctiveness enhancer. The equilibrium loss prevents excessive reliance on specific experts, while the distinctiveness enhancer encourages each expert to specialize in different aspects of the data, thereby promoting diversity in learned representations. Comprehensive experiments on various multi-view benchmark datasets demonstrate the superiority of DMVC-CE compared to state-of-the-art MVC baselines.

AAAI Conference 2025 Conference Paper

Motion-aware Contrastive Learning for Temporal Panoptic Scene Graph Generation

• Thong Thanh Nguyen
• Xiaobao Wu
• Yi Bin
• Cong-Duy T Nguyen
• See-Kiong Ng
• Anh Tuan Luu

To equip artificial intelligence with a comprehensive understanding towards a temporal world, video and 4D panoptic scene graph generation abstracts visual data into nodes to represent entities and edges to capture temporal relations. Existing methods encode entity masks tracked across temporal dimensions (mask tubes), then predict their relations with temporal pooling operation, which does not fully utilize the motion indicative of the entities' relation. To overcome this limitation, we introduce a contrastive representation learning framework that focuses on motion pattern for temporal scene graph generation. Firstly, our framework encourages the model to learn close representations for mask tubes of similar subject-relation-object triplets. Secondly, we seek to push apart mask tubes from their temporally shuffled versions. Moreover, we also learn distant representations for mask tubes belonging to the same video but different triplets. Extensive experiments show that our motion-aware contrastive framework significantly improves state-of-the-art methods on both video and 4D datasets.

AAAI Conference 2025 Conference Paper

Multi-Scale Contrastive Learning for Video Temporal Grounding

• Thong Thanh Nguyen
• Yi Bin
• Xiaobao Wu
• Zhiyuan Hu
• Cong-Duy T Nguyen
• See-Kiong Ng
• Anh Tuan Luu

Temporal grounding, which localizes video moments related to a natural language query, is a core problem of vision-language learning and video understanding. To encode video moments of varying lengths, recent methods employ a multi-level structure known as a feature pyramid. In this structure, lower levels concentrate on short-range video moments, while higher levels address long-range moments. Because higher levels experience downsampling to accommodate increasing moment length, their capacity to capture information is reduced and consequently leads to degraded information in moment representations. To resolve this problem, we propose a contrastive learning framework to capture salient semantics among video moments. Our key methodology is to leverage samples from the feature space emanating from multiple stages of the video encoder itself requiring neither data augmentation nor online memory banks to obtain positive and negative samples. To enable such an extension, we introduce a sampling process to draw multiple video moments corresponding to a common query. Subsequently, by utilizing these moments' representations across video encoder layers, we instantiate a novel form of multi-scale and cross-scale contrastive learning that links local short-range video moments with global long-range video moments. Extensive experiments demonstrate the effectiveness of our framework for not only long-form but also short-form video grounding.

ICLR Conference 2025 Conference Paper

PIED: Physics-Informed Experimental Design for Inverse Problems

• Apivich Hemachandra
• Gregory Kang Ruey Lau
• See-Kiong Ng
• Bryan Kian Hsiang Low

In many science and engineering settings, system dynamics are characterized by governing partial differential equations (PDEs), and a major challenge is to solve inverse problems (IPs) where unknown PDE parameters are inferred based on observational data gathered under limited budget. Due to the high costs of setting up and running experiments, experimental design (ED) is often done with the help of PDE simulations to optimize for the most informative design parameters (e.g., sensor placements) to solve such IPs, prior to actual data collection. This process of optimizing design parameters is especially critical when the budget and other practical constraints make it infeasible to adjust the design parameters between trials during the experiments. However, existing experimental design (ED) methods tend to require sequential and frequent design parameter adjustments between trials. Furthermore, they also have significant computational bottlenecks due to the need for complex numerical simulations for PDEs, and do not exploit the advantages provided by physics informed neural networks (PINNs) in solving IPs for PDE-governed systems, such as its meshless solutions, differentiability, and amortized training. This work presents Physics-Informed Experimental Design (PIED), the first ED framework that makes use of PINNs in a fully differentiable architecture to perform continuous optimization of design parameters for IPs for one-shot deployments. PIED overcomes existing methods' computational bottlenecks through parallelized computation and meta-learning of PINN parameter initialization, and proposes novel methods to effectively take into account PINN training dynamics in optimizing the ED parameters. Through experiments based on noisy simulated data and even real world experimental data, we empirically show that given limited observation budget, PIED significantly outperforms existing ED methods in solving IPs, including for challenging settings where the inverse parameters are unknown functions rather than just finite-dimensional.

NeurIPS Conference 2025 Conference Paper

Self-Perturbed Anomaly-Aware Graph Dynamics for Multivariate Time-Series Anomaly Detection

• Jinyu Cai
• Yuan Xie
• Glynnis Lim
• Yifang Yin
• Roger Zimmermann
• See-Kiong Ng

Detecting anomalies in multivariate time-series data is an essential task across various domains, yet there are unresolved challenges such as (1) severe class imbalance between normal and anomalous data due to rare anomaly availability in the real world; (2) limited adaptability of the static graph-based methods to dynamically changing inter-variable correlations; and (3) neglect of subtle anomalies due to overfitting to normal patterns in reconstruction-based methods. To tackle these issues, we propose Self-Perturbed Anomaly-Aware Graph Dynamics (SPAGD), a framework for time-series anomaly detection. SPAGD employs a self-perturbation module that generates self-perturbed time series from the reconstruction process of normal ones, which provide auxiliary signals to alleviate class imbalance during training. Concurrently, an anomaly-aware graph construction module is proposed to dynamically adjust the graph structure by leveraging the reconstruction residuals of self-perturbed time series, thereby emphasizing the inter-variable disruptions induced by anomalous candidates. A unified spatio-temporal anomaly detection module then integrates both spatial and temporal convolutions to train a classifier that distinguishes normal time series from the auxiliary self-perturbed samples. Extensive experiments across multiple benchmark datasets demonstrate the effectiveness of SPAGD compared to state-of-the-art baselines.

IJCAI Conference 2025 Conference Paper

Taking STEPS Forward: Enhancing Online Peer-Counseling with Schema Therapy via Socratic Questioning

• Beng Heng Ang
• Sujatha Das Gollapalli
• See-Kiong Ng

Peer-counseling is essential in online mental health communities to provide relatable support to those seeking help, but the peer-counselors often lack professional training in therapeutic counseling to produce the desired cognitive changes. In this paper, we present STEPS, an AI-powered assistive dialog tool for peer-counseling. Unlike other existing tools, STEPS assists peer-counselors in facilitating cognitive change in online counseling settings. Towards this goal, we emulate two key phases in a Schema Therapy-based in-person counseling session–(1) Schema Assessment to uncover the deep-seated irrational beliefs underlying an individual’s mental health problems, and (2) Cognitive Change to reframe these beliefs into healthier alternatives. In both phases, we employ Socratic questioning techniques to effectively elicit critical introspection and guide cognitive change. We describe STEPS and present expert evaluation studies on its counseling conversations on real-world mental health forum posts. Our results indicate that STEPS significantly outperforms competitive baselines on all key metrics related to schema assessment, cognitive change strategies, and critical thinking, achieving an impressive average rating of 5 out of 6, highlighting its strong potential as a transformative tool for online peer-counseling.

AAAI Conference 2025 Conference Paper

Towards Verifiable Text Generation with Generative Agent

• Bin Ji
• Huijun Liu
• Mingzhe Du
• Shasha Li
• Xiaodong Liu
• Jun Ma
• Jie Yu
• See-Kiong Ng

Text generation with citations makes it easy to verify the factuality of Large Language Models’ (LLMs) generations. Existing one-step generation studies expose distinct shortages in answer refinement and in-context demonstration matching. In light of these challenges, we propose R2-MGA, a Retrieval and Reflection Memory-augmented Generative Agent. Specifically, it first retrieves the memory bank to obtain the best-matched memory snippet, then reflects the retrieved snippet as a reasoning rationale, next combines the snippet and the rationale as the best-matched in-context demonstration. Additionally, it is capable of in-depth answer refinement with two specifically designed modules. We evaluate R2-MGA across five LLMs on the ALCE benchmark. The results reveal R2-MGA’ exceptional capabilities in text generation with citations. In particular, compared to the selected baselines, it delivers up to +58.8% and +154.7% relative performance gains on answer correctness and citation quality, respectively. Extensive analyses strongly support the motivations of R2-MGA.

AAAI Conference 2024 Conference Paper

Chain-of-Thought Improves Text Generation with Citations in Large Language Models

• Bin Ji
• Huijun Liu
• Mingzhe Du
• See-Kiong Ng

Previous studies disclose that Large Language Models (LLMs) suffer from hallucinations when generating texts, bringing a novel and challenging research topic to the public, which centers on enabling LLMs to generate texts with citations. Existing work exposes two limitations when using LLMs to generate answers to questions with provided documents: unsatisfactory answer correctness and poor citation quality. To tackle the above issues, we investigate using Chain-of-Thought (CoT) to elicit LLMs’ ability to synthesize correct answers from multiple documents, as well as properly cite these documents. Moreover, we propose a Citation Insurance Mechanism, which enables LLMs to detect and cite those missing citations. We conduct experiments on the ALCE benchmark with six open-source LLMs. Experimental results demonstrate that: (1) the CoT prompting strategy significantly improves the quality of text generation with citations; (2) the Citation Insurance Mechanism delivers impressive gains in citation quality at a low cost; (3) our best approach performs comparably as previous best ChatGPT-based baselines. Extensive analyses further validate the effectiveness of the proposed approach.

ECAI Conference 2024 Conference Paper

Counseling Responses for Mental Health Forum Questions with Early Maladaptive Schema Prediction

• Sujatha Das Gollapalli
• Beng Heng Ang
• Mingzhe Du
• See-Kiong Ng

State-of-the-art Large Language Models (LLMs) have shown remarkable capabilities for general Question Answering (QA) tasks. However, their practical use for answering mental health questions has been limited due to the missing link between LLM-generated answer responses and well-established theories and guiding principles from Psychology and Counseling. We present a first step in this direction with STeer, an AI-based method that supports Schema Therapy-enabled responses for mental health questions on community QA forums. STeer uses Early Maladaptive Schemas (EMSs), a fundamental concept from Schema Therapy that characterizes “self-defeating, unhealthy patterns of thought and behavior” in individuals, to effectively prompt state-of-the-art LLMs to generate specific, theoretically-grounded, empathetic counseling responses to mental health questions. We present EMSRank, a novel method based on the Personalized PageRank algorithm, to automatically predict the EMSs from mental health forum question texts. We show that EMSRank is computationally scalable and can be further combined with textual entailment to obtain high precision, explainable EMS labels for mental health forum questions. To address the current lack of annotated datasets, we also leveraged on EMSRank to create a first-of-its-kind, large dataset of about 23K EMS-annotated mental health questions from three diverse, currently operating, peer-support community forums for mental health. With the global rise in mental health issues, our work is a timely step towards enabling the use of AI-based assistive tools for counseling support on mental health community forums.

ICML Conference 2024 Conference Paper

Distributionally Robust Data Valuation

• Xiaoqiang Lin
• Xinyi Xu
• Zhaoxuan Wu
• See-Kiong Ng
• Bryan Kian Hsiang Low

Data valuation quantifies the contribution of each data point to the performance of a machine learning model. Existing works typically define the value of data by its improvement of the validation performance of the trained model. However, this approach can be impractical to apply in collaborative machine learning and data marketplace since it is difficult for the parties/buyers to agree on a common validation dataset or determine the exact validation distribution a priori. To address this, we propose a distributionally robust data valuation approach to perform data valuation without known/fixed validation distributions. Our approach defines the value of data by its improvement of the distributionally robust generalization error (DRGE), thus providing a worst-case performance guarantee without a known/fixed validation distribution. However, since computing DRGE directly is infeasible, we propose using model deviation as a proxy for the marginal improvement of DRGE (for kernel regression and neural networks) to compute data values. Furthermore, we identify a notion of uniqueness where low uniqueness characterizes low-value data. We empirically demonstrate that our approach outperforms existing data valuation approaches in data selection and data removal tasks on real-world datasets (e. g. , housing price prediction, diabetes hospitalization prediction).

IJCAI Conference 2024 Conference Paper

From 2D to 3D: AISG-SLA Visual Localization Challenge

• Jialin Gao
• Bill Ong
• Darld Lwi
• Zhen Hao Ng
• Xun Wei Yee
• Mun-Thye Mak
• Wee Siong Ng
• See-Kiong Ng

Research in 3D mapping is crucial for smart city applications, yet the cost of acquiring 3D data often hinders progress. Visual localization, particularly monocular camera position estimation, offers a solution by determining the camera's pose solely through visual cues. However, this task is challenging due to limited data from a single camera. To tackle these challenges, we organized the AISG–SLA Visual Localization Challenge (VLC) at IJCAI 2023 to explore how AI can accurately extract camera pose data from 2D images in 3D space. The challenge attracted over 300 participants worldwide, forming 50+ teams. Winning teams achieved high accuracy in pose estimation using images from a car-mounted camera with low frame rates. The VLC dataset is available for research purposes upon request via vlc-dataset@aisingapore. org.

AAAI Conference 2024 System Paper

From Static to Dynamic: Knowledge Metabolism for Large Language Models

• Mingzhe Du
• Anh Tuan Luu
• Bin Ji
• See-Kiong Ng

The immense parameter space of Large Language Models (LLMs) endows them with superior knowledge retention capabilities, allowing them to excel in a variety of natural language processing tasks. However, it also instigates difficulties in consistently tuning LMs to incorporate the most recent knowledge, which may further lead LMs to produce inaccurate and fabricated content. To alleviate this issue, we propose a knowledge metabolism framework for LLMs. This framework proactively sustains the credibility of knowledge through an auxiliary external memory component and directly delivers pertinent knowledge for LM inference, thereby suppressing hallucinations caused by obsolete internal knowledge during the LM inference process. Benchmark experiments demonstrate DynaMind's effectiveness in overcoming this challenge. The code and demo of DynaMind are available at: https://github.com/Elfsong/DynaMind.

IJCAI Conference 2024 Conference Paper

LG-FGAD: An Effective Federated Graph Anomaly Detection Framework

• Jinyu Cai
• Yunhe Zhang
• Jicong Fan
• See-Kiong Ng

Graph anomaly detection (GAD), which aims to identify those graphs that are significantly different from other ones, has gained growing attention in many real-world scenarios. However, existing GAD methods are generally designed for centralized training, while in real-world collaboration, graph data is generally distributed across various clients and exhibits significant non-IID characteristics. To tackle this challenge, we propose a federated graph anomaly detection framework with local-global anomaly awareness (LG-FGAD). We first introduce a self-adversarial generation module and train a discriminator to identify the generated anomalous graphs from the normal graph. To enhance the anomaly awareness of the model, we propose to maximize/minimize the mutual information from local and global perspectives. Importantly, to alleviate the impact of non-IID problems in collaborative learning, we propose a dual knowledge distillation module. The knowledge distillation is conducted over both logits and embedding distributions, and only the student model engages in collaboration to preserve the personalization of each client. Empirical results on various types of real-world datasets prove the superiority of our method.

NeurIPS Conference 2024 Conference Paper

Localized Zeroth-Order Prompt Optimization

• Wenyang Hu
• Yao Shu
• Zongmin Yu
• Zhaoxuan Wu
• Xiaoqiang Lin
• Zhongxiang Dai
• See-Kiong Ng
• Bryan Kian Hsiang Low

The efficacy of large language models (LLMs) in understanding and generating natural language has aroused a wide interest in developing prompt-based methods to harness the power of black-box LLMs. Existing methodologies usually prioritize a global optimization for finding the global optimum, which however will perform poorly in certain tasks. This thus motivates us to re-think the necessity of finding a global optimum in prompt optimization. To answer this, we conduct a thorough empirical study on prompt optimization and draw two major insights. Contrasting with the rarity of global optimum, local optima are usually prevalent and well-performed, which can be more worthwhile for efficient prompt optimization ( Insight I ). The choice of the input domain, covering both the generation and the representation of prompts, affects the identification of well-performing local optima ( Insight II ). Inspired by these insights, we propose a novel algorithm, namely localized zeroth-order prompt optimization (ZOPO), which incorporates a Neural Tangent Kernel-based derived Gaussian process into standard zeroth-order optimization for an efficient search of well-performing local optima in prompt optimization. Remarkably, ZOPO outperforms existing baselines in terms of both the optimization performance and the query efficiency, which we demonstrate through extensive experiments.

NeurIPS Conference 2024 Conference Paper

Mercury: A Code Efficiency Benchmark for Code Large Language Models

• Mingzhe Du
• Luu A. Tuan
• Bin Ji
• Qian Liu
• See-Kiong Ng

Amidst the recent strides in evaluating Large Language Models for Code (Code LLMs), existing benchmarks have mainly focused on the functional correctness of generated code, neglecting the importance of their computational efficiency. To fill the gap, we present Mercury, the first code efficiency benchmark for Code LLMs. It comprises 1, 889 Python tasks, each accompanied by adequate solutions that serve as real-world efficiency baselines, enabling a comprehensive analysis of the runtime distribution. Based on the distribution, we introduce a new metric Beyond, which computes a runtime-percentile-weighted Pass score to reflect functional correctness and code efficiency simultaneously. On Mercury, leading Code LLMs can achieve 65% on Pass, while less than 50% on Beyond. Given that an ideal Beyond score would be aligned with the Pass score, it indicates that while Code LLMs exhibit impressive capabilities in generating functionally correct code, there remains a notable gap in their efficiency. Finally, our empirical experiments reveal that Direct Preference Optimization (DPO) serves as a robust baseline for enhancing code efficiency compared with Supervised Fine Tuning (SFT), which paves a promising avenue for future exploration of efficient code generation. Our code and data are available on GitHub: https: //github. com/Elfsong/Mercury.

ICLR Conference 2024 Conference Paper

PINNACLE: PINN Adaptive ColLocation and Experimental points selection

• Gregory Kang Ruey Lau
• Apivich Hemachandra
• See-Kiong Ng
• Bryan Kian Hsiang Low

Physics-Informed Neural Networks (PINNs), which incorporate PDEs as soft constraints, train with a composite loss function that contains multiple training point types: different types of collocation points chosen during training to enforce each PDE and initial/boundary conditions, and experimental points which are usually costly to obtain via experiments or simulations. Training PINNs using this loss function is challenging as it typically requires selecting large numbers of points of different types, each with different training dynamics. Unlike past works that focused on the selection of either collocation or experimental points, this work introduces PINN Adaptive ColLocation and Experimental points selection (PINNACLE), the first algorithm that jointly optimizes the selection of all training point types, while automatically adjusting the proportion of collocation point types as training progresses. PINNACLE uses information on the interactions among training point types, which had not been considered before, based on an analysis of PINN training dynamics via the Neural Tangent Kernel (NTK). We theoretically show that the criterion used by PINNACLE is related to the PINN generalization error, and empirically demonstrate that PINNACLE is able to outperform existing point selection methods for forward, inverse, and transfer learning problems.

ICLR Conference 2024 Conference Paper

Plug-and-Play Policy Planner for Large Language Model Powered Dialogue Agents

• Yang Deng 0002
• Wenxuan Zhang 0001
• Wai Lam
• See-Kiong Ng
• Tat-Seng Chua

Proactive dialogues serve as a practical yet challenging dialogue problem in the era of large language models (LLMs), where the dialogue policy planning is the key to improving the proactivity of LLMs. Most existing studies enable the dialogue policy planning of LLMs using various prompting schemes or iteratively enhance this capability in handling the given case with verbal AI feedback. However, these approaches are either bounded by the policy planning capability of the frozen LLMs or hard to be transferred to new cases. In this work, we introduce a new dialogue policy planning paradigm to strategize LLMs for proactive dialogue problems with a tunable language model plug-in as a plug-and-play dialogue policy planner, named PPDPP. Specifically, we develop a novel training framework to facilitate supervised fine-tuning over available human-annotated data as well as reinforcement learning from goal-oriented AI feedback with dynamic interaction data collected by the LLM-based self-play simulation. In this manner, the LLM-powered dialogue agent can not only be generalized to different cases after the training, but also be applicable to different applications by just substituting the learned plug-in. In addition, we propose to evaluate the policy planning capability of dialogue systems under the interactive setting. Experimental results demonstrate that PPDPP consistently and substantially outperforms existing approaches on three different proactive dialogue applications, including negotiation, emotional support, and tutoring dialogues.

NeurIPS Conference 2024 Conference Paper

Prompt Optimization with EASE? Efficient Ordering-aware Automated Selection of Exemplars

• Zhaoxuan Wu
• Xiaoqiang Lin
• Zhongxiang Dai
• Wenyang Hu
• Yao Shu
• See-Kiong Ng
• Patrick Jaillet
• Bryan Kian Hsiang Low

Large language models (LLMs) have shown impressive capabilities in real-world applications. The capability of *in-context learning* (ICL) allows us to adapt an LLM to downstream tasks by including input-label exemplars in the prompt without model fine-tuning. However, the quality of these exemplars in the prompt greatly impacts performance, highlighting the need for an effective automated exemplar selection method. Recent studies have explored retrieval-based approaches to select exemplars tailored to individual test queries, which can be undesirable due to extra test-time computation and an increased risk of data exposure. Moreover, existing methods fail to adequately account for the impact of exemplar ordering on the performance. On the other hand, the impact of the *instruction*, another essential component in the prompt given to the LLM, is often overlooked in existing exemplar selection methods. To address these challenges, we propose a novel method named $\texttt{EASE}$, which leverages the hidden embedding from a pre-trained language model to represent ordered sets of exemplars and uses a neural bandit algorithm to optimize the sets of exemplars *while accounting for exemplar ordering*. Our $\texttt{EASE}$ can efficiently find an ordered set of exemplars that *performs well for all test queries* from a given task, thereby eliminating test-time computation. Importantly, $\texttt{EASE}$ can be readily extended to *jointly optimize both the exemplars and the instruction*. Through extensive empirical evaluations (including novel tasks), we demonstrate the superiority of $\texttt{EASE}$ over existing methods, and reveal practical insights about the impact of exemplar selection on ICL, which may be of independent interest. Our code is available at https: //github. com/ZhaoxuanWu/EASE-Prompt-Optimization.

AAAI Conference 2024 Conference Paper

READ-PVLA: Recurrent Adapter with Partial Video-Language Alignment for Parameter-Efficient Transfer Learning in Low-Resource Video-Language Modeling

• Thong Nguyen
• Xiaobao Wu
• Xinshuai Dong
• Khoi M. Le
• Zhiyuan Hu
• Cong-Duy Nguyen
• See-Kiong Ng
• Anh Tuan Luu

Fully fine-tuning pretrained large-scale transformer models has become a popular paradigm for video-language modeling tasks, such as temporal language grounding and video-language summarization. With a growing number of tasks and limited training data, such full fine-tuning approach leads to costly model storage and unstable training. To overcome these shortcomings, we introduce lightweight adapters to the pre-trained model and only update them at fine-tuning time. However, existing adapters fail to capture intrinsic temporal relations among video frames or textual words. Moreover, they neglect the preservation of critical task-related information that flows from the raw video-language input into the adapter’s low-dimensional space. To address these issues, we first propose a novel REcurrent ADapter (READ) that employs recurrent computation to enable temporal modeling capability. Second, we propose Partial Video-Language Alignment (PVLA) objective via the use of partial optimal transport to maintain task-related information flowing into our READ modules. We validate our READ-PVLA framework through extensive experiments where READ-PVLA significantly outperforms all existing fine-tuning strategies on multiple low-resource temporal language grounding and video-language summarization benchmarks.

ICLR Conference 2024 Conference Paper

Topic Modeling as Multi-Objective Contrastive Optimization

• Thong Thanh Nguyen
• Xiaobao Wu
• Xinshuai Dong
• Cong-Duy T. Nguyen
• See-Kiong Ng
• Anh Tuan Luu

Recent representation learning approaches enhance neural topic models by optimizing the weighted linear combination of the evidence lower bound (ELBO) of the log-likelihood and the contrastive learning objective that contrasts pairs of input documents. However, document-level contrastive learning might capture low-level mutual information, such as word ratio, which disturbs topic modeling. Moreover, there is a potential conflict between the ELBO loss that memorizes input details for better reconstruction quality, and the contrastive loss which attempts to learn topic representations that generalize among input documents. To address these issues, we first introduce a novel contrastive learning method oriented towards sets of topic vectors to capture useful semantics that are shared among a set of input documents. Secondly, we explicitly cast contrastive topic modeling as a gradient-based multi-objective optimization problem, with the goal of achieving a Pareto stationary solution that balances the trade-off between the ELBO and the contrastive objective. Extensive experiments demonstrate that our framework consistently produces higher-performing neural topic models in terms of topic coherence, topic diversity, and downstream performance.

NeurIPS Conference 2024 Conference Paper

Uncertainty of Thoughts: Uncertainty-Aware Planning Enhances Information Seeking in LLMs

• Zhiyuan Hu
• Chumin Liu
• Xidong Feng
• Yilun Zhao
• See-Kiong Ng
• Anh T. Luu
• Junxian He
• Pang W. Koh

In the face of uncertainty, the ability to seek information is of fundamental importance. In many practical applications, such as medical diagnosis and troubleshooting, the information needed to solve the task is not initially given, and has to be actively sought by asking follow-up questions (for example, a doctor asking a patient for more details about their symptoms). In this work, we introduce Uncertainty of Thoughts (UoT), an algorithm to augment large language models with the ability to actively seek information by asking effective questions. UoT combines: 1. An uncertainty-aware simulation approach which enables the model to simulate possible future scenarios and how likely they are to occur, 2. Uncertainty-based rewards motivated by information gain which incentivizes the model to seek information, and3. A reward propagation scheme to select the optimal question to ask in a way that maximizes the expected reward. In experiments on medical diagnosis, troubleshooting and the `20 Questions' game, UoT achieves an average performance improvement of 38. 1% in the rate of successful task completion across multiple LLMs compared with direct prompting, and also improves efficiency (i. e. , the number of questions needed to complete the task).

TMLR Journal 2024 Journal Article

Uniformly Distributed Feature Representations for Fair and Robust Learning

• Kiran Krishnamachari
• See-Kiong Ng
• Chuan-Sheng Foo

A fundamental challenge in machine learning is training models that generalize well to distributions different from the training distribution. Empirical Risk Minimization (ERM), which is the predominant learning principle, is known to under-perform in minority sub-populations and fail to generalize well in unseen test domains. In this work, we propose a novel learning principle called Uniform Risk Minimization (URM) to alleviate these issues. We first show theoretically that uniform training data distributions and feature representations support robustness to distribution shifts. Motivated by this result, we propose an empirical method that trains deep neural networks to learn a uniformly distributed feature representation in their final activation layer for improved robustness. Our experiments on multiple datasets for sub-population shifts and domain generalization show that URM improves the generalization of deep neural networks without requiring knowledge of groups or domains during training. URM is competitive with the best existing methods designed for these tasks and can also be easily combined with them for improved performance. Our work sheds light on the importance of the distribution of learned feature representations for model robustness and fairness. Code is available at https://github.com/kiranchari/UniformRiskMinimization.

ICML Conference 2024 Conference Paper

Use Your INSTINCT: INSTruction optimization for LLMs usIng Neural bandits Coupled with Transformers

• Xiaoqiang Lin
• Zhaoxuan Wu
• Zhongxiang Dai
• Wenyang Hu
• Yao Shu
• See-Kiong Ng
• Patrick Jaillet
• Bryan Kian Hsiang Low

Large language models (LLMs) have shown remarkable instruction-following capabilities and achieved impressive performances in various applications. However, the performances of LLMs depend heavily on the instructions given to them, which are typically manually tuned with substantial human efforts. Recent work has used the query-efficient Bayesian optimization (BO) algorithm to automatically optimize the instructions given to black-box LLMs. However, BO usually falls short when optimizing highly sophisticated (e. g. , high-dimensional) objective functions, such as the functions mapping an instruction to the performance of an LLM. This is mainly due to the limited expressive power of the Gaussian process (GP) which is used by BO as a surrogate to model the objective function. Meanwhile, it has been repeatedly shown that neural networks (NNs), especially pre-trained transformers, possess strong expressive power and can model highly complex functions. So, we adopt a neural bandit algorithm which replaces the GP in BO by an NN surrogate to optimize instructions for black-box LLMs. More importantly, the neural bandit algorithm allows us to naturally couple the NN surrogate with the hidden representation learned by a pre-trained transformer (i. e. , an open-source LLM), which significantly boosts its performance. These motivate us to propose our INSTruction optimization usIng Neural bandits Coupled with Transformers (INSTINCT) algorithm. We perform instruction optimization for ChatGPT and use extensive experiments to show that INSTINCT consistently outperforms baselines in different tasks, e. g. , various instruction induction tasks and the task of improving zero-shot chain-of-thought instructions. Our code is available at https: //github. com/xqlin98/INSTINCT.

IJCAI Conference 2023 Conference Paper

COOL, a Context Outlooker, and Its Application to Question Answering and Other Natural Language Processing Tasks

• Fangyi Zhu
• See-Kiong Ng
• Stéphane Bressan

Vision outlooker improves the performance of vision transformers, which implements a self-attention mechanism by adding an outlook attention, a form of local attention. In natural language processing, as has been the case in computer vision and other domains, transformer-based models constitute the state-of-the-art for most processing tasks. In this domain, too, many authors have argued and demonstrated the importance of local context. We present an outlook attention mechanism, COOL, for natural language processing. COOL, added on top of the self-attention layers of a transformer-based model, encodes local syntactic context considering word proximity and more pair-wise constraints than dynamic convolution used by existing approaches. A comparative empirical performance evaluation of an implementation of COOL with different transformer-based models confirms the opportunity for improvement over a baseline using the original models alone for various natural language processing tasks, including question answering. The proposed approach achieves competitive performance with existing state-of-the-art methods on some tasks.

TMLR Journal 2023 Journal Article

Data-Free Diversity-Based Ensemble Selection for One-Shot Federated Learning

• Naibo Wang
• Wenjie Feng
• yuchen deng
• Moming Duan
• Fusheng Liu
• See-Kiong Ng

The emerging availability of various machine learning models creates a great demand to harness the collective intelligence of many independently well-trained models to improve overall performance. Considering the privacy concern and non-negligible communication costs, one-shot federated learning and ensemble learning in a data-free manner attract significant attention. However, conventional ensemble selection approaches are neither training efficient nor applicable to federated learning due to the risk of privacy leakage from local clients; meanwhile, the "many could be better than all" principle under data-free constraints makes it even more challenging. Therefore, it becomes crucial to design an effective ensemble selection strategy to find a good subset of the base models as the ensemble team for the federated learning scenario. In this paper, we propose a novel data-free diversity-based framework, DeDES, to address the ensemble selection problem with diversity consideration for models under the one-shot federated learning setting. Experimental results show that our method can achieve both better performance and higher efficiency over 5 datasets, 4 different model structures, and both homogeneous and heterogeneous model groups under four different data-partition strategies.

ICML Conference 2023 Conference Paper

Fair yet Asymptotically Equal Collaborative Learning

• Xiaoqiang Lin
• Xinyi Xu
• See-Kiong Ng
• Chuan-Sheng Foo
• Bryan Kian Hsiang Low

In collaborative learning with streaming data, nodes (e. g. , organizations) jointly and continuously learn a machine learning (ML) model by sharing the latest model updates computed from their latest streaming data. For the more resourceful nodes to be willing to share their model updates, they need to be fairly incentivized. This paper explores an incentive design that guarantees fairness so that nodes receive rewards commensurate to their contributions. Our approach leverages an explore-then-exploit formulation to estimate the nodes’ contributions (i. e. , exploration) for realizing our theoretically guaranteed fair incentives (i. e. , exploitation). However, we observe a "rich get richer" phenomenon arising from the existing approaches to guarantee fairness and it discourages the participation of the less resourceful nodes. To remedy this, we additionally preserve asymptotic equality, i. e. , less resourceful nodes achieve equal performance eventually to the more resourceful/“rich” nodes. We empirically demonstrate in two settings with real-world streaming data: federated online incremental learning and federated reinforcement learning, that our proposed approach outperforms existing baselines in fairness and learning performance while remaining competitive in preserving equality.

AAAI Conference 2023 System Paper

Generating Reflective Questions for Engaging Gallery Visitors in ArtMuse

• Sujatha Das Gollapalli
• Mingzhe Du
• See-Kiong Ng

Human guides in museums and galleries are professionally trained to stimulate informal learning in visitors by asking low-risk, open-ended reflective questions that enable them to focus on specific features of artifacts, relate to prior experiences, and elicit curiosity as well as further thought. We present ArtMuse, our AI-powered chatbot for asking reflective questions in context of paintings. Our reflective question generation model in ArtMuse was trained by applying a novel combination of existing models for extractive question answering and open-domain chitchat. User evaluation studies indicate that we are able to generate fluent and specific reflective questions for paintings that are highly-engaging.

TMLR Journal 2023 Journal Article

Mitigating Real-World Distribution Shifts in the Fourier Domain

• Kiran Krishnamachari
• See-Kiong Ng
• Chuan-Sheng Foo

While machine learning systems can be highly accurate in their training environments, their performance in real-world deployments can suffer significantly due to distribution shifts. Real-world distribution shifts involve various input distortions due to noise, weather, device and other variations. Many real-world distribution shifts are not represented in standard domain adaptation datasets and prior empirical work has shown that domain adaptation methods developed using these standard datasets may not generalize well to real-world distribution shifts. Furthermore, motivated by observations of the sensitivity of deep neural networks (DNN) to the spectral statistics of data, which can vary in real-world scenarios, we propose Fourier Moment Matching (FMM), a model-agnostic input transformation that matches the Fourier-amplitude statistics of source to target data using unlabeled samples. We demonstrate through extensive empirical evaluations across time-series, image classification and semantic segmentation tasks that FMM is effective both individually and when combined with a variety of existing methods to overcome real-world distribution shifts. Code is available at https://github.com/kiranchari/FourierMomentMatching.

ICML Conference 2023 Conference Paper

Training-Free Neural Active Learning with Initialization-Robustness Guarantees

• Apivich Hemachandra
• Zhongxiang Dai
• Jasraj Singh
• See-Kiong Ng
• Bryan Kian Hsiang Low

Existing neural active learning algorithms have aimed to optimize the predictive performance of neural networks (NNs) by selecting data for labelling. However, other than a good predictive performance, being robust against random parameter initializations is also a crucial requirement in safety-critical applications. To this end, we introduce our expected variance with Gaussian processes (EV-GP) criterion for neural active learning, which is theoretically guaranteed to select data points which lead to trained NNs with both (a) good predictive performances and (b) initialization robustness. Importantly, our EV-GP criterion is training-free, i. e. , it does not require any training of the NN during data selection, which makes it computationally efficient. We empirically demonstrate that our EV-GP criterion is highly correlated with both initialization robustness and generalization performance, and show that it consistently outperforms baseline methods in terms of both desiderata, especially in situations with limited initial data or large batch sizes.

TMLR Journal 2022 Journal Article

Fourier Sensitivity and Regularization of Computer Vision Models

• Kiran Krishnamachari
• See-Kiong Ng
• Chuan-Sheng Foo

Recent work has empirically shown that deep neural networks latch on to the Fourier statistics of training data and show increased sensitivity to Fourier-basis directions in the input. Understanding and modifying this Fourier-sensitivity of computer vision models may help improve their robustness, hence, in this paper we study the frequency sensitivity characteristics of deep neural networks using a principled approach. We first propose a $\textbf{\textit{basis trick}}$, proving that unitary transformations of the input-gradient of a function can be used to compute its gradient in the basis induced by the transformation. Using this result, we propose a general measure of any differentiable computer vision model's $\textit{\textbf{Fourier-sensitivity}}$ using the unitary Fourier-transform of its input-gradient. When applied to deep neural networks, we find that computer vision models are consistently sensitive to particular frequencies dependent on the dataset, training method and architecture. Based on this measure, we further propose a $\textit{\textbf{Fourier-regularization}}$ framework to modify the Fourier-sensitivities and frequency bias of models. Using our proposed regularizer-family, we demonstrate that deep neural networks obtain improved classification accuracy on robustness evaluations.

AAAI Conference 2022 Conference Paper

LUNAR: Unifying Local Outlier Detection Methods via Graph Neural Networks

• Adam Goodge
• Bryan Hooi
• See-Kiong Ng
• Wee Siong Ng

Many well-established anomaly detection methods use the distance of a sample to those in its local neighbourhood: socalled ‘local outlier methods’, such as LOF and DBSCAN. They are popular for their simple principles and strong performance on unstructured, feature-based data that is commonplace in many practical applications. However, they cannot learn to adapt for a particular set of data due to their lack of trainable parameters. In this paper, we begin by unifying local outlier methods by showing that they are particular cases of the more general message passing framework used in graph neural networks. This allows us to introduce learnability into local outlier methods, in the form of a neural network, for greater flexibility and expressivity: specifically, we propose LUNAR, a novel, graph neural network-based anomaly detection method. LUNAR learns to use information from the nearest neighbours of each node in a trainable way to find anomalies. We show that our method performs significantly better than existing local outlier methods, as well as state-ofthe-art deep baselines. We also show that the performance of our method is much more robust to different settings of the local neighbourhood size.

AAAI Conference 2011 Conference Paper

Integrating Community Question and Answer Archives

• Wei Wei
• Gao Cong
• Xiaoli Li
• See-Kiong Ng
• Guohui Li

Question and answer pairs in Community Question Answering (CQA) services are organized into hierarchical structures or taxonomies to facilitate users to find the answers for their questions conveniently. We observe that different CQA services have their own knowledge focus and used different taxonomies to organize their question and answer pairs in their archives. As there are no simple semantic mappings between the taxonomies of the CQA services, the integration of CQA services is a challenging task. The existing approaches on integrating taxonomies ignore the hierarchical structures of the source taxonomy. In this paper, we propose a novel approach that is capable of incorporating the parent-child and sibling information in the hierarchical structures of the source taxonomy for accurate taxonomy integration. Our experimental results with real world CQA data demonstrate that the proposed method significantly outperforms state-of-the-art methods.

IJCAI Conference 2011 Conference Paper

Positive Unlabeled Leaning for Time Series Classification

• Minh Nhut Nguyen
• Xiaoli-Li Li
• See-Kiong Ng

In many real-world applications of the time series classification problem, not only could the negative training instances be missing, the number of positive instances available for learning may also be rather limited. This has motivated the development of new classification algorithms that can learn from a small set P of labeled seed positive instances augmented with a set U of unlabeled instances (i. e. PU learning algorithms). However, existing PU learning algorithms for time series classification have less than satisfactory performance as they are unable to identify the class boundary between positive and negative instances accurately. In this paper, we propose a novel PU learning algorithm LCLC (Learning from Common Local Clusters) for time series classification. LCLC is designed to effectively identify the ground truths' positive and negative boundaries, resulting in more accurate classifiers than those constructed using existing methods. We have applied LCLC to classify time series data from different application domains; the experimental results demonstrate that LCLC outperforms existing methods significantly.

IJCAI Conference 2007 Conference Paper

• Xiao-li Li
• Bing Liu
• See-Kiong Ng

Traditional classification involves building a clas-sifier using labeled training examples from a set of predefined classes and then applying the classifier to classify test instances into the same set of classes. In practice, this paradigm can be problematic be-cause the test data may contain instances that do not belong to any of the previously defined classes. Detecting such unexpected instances in the test set is an important issue in practice. The problem can be formulated as learning from positive and unla-beled examples (PU learning). However, current PU learning algorithms require a large proportion of negative instances in the unlabeled set to be effec-tive. This paper proposes a novel technique to solve this problem in the text classification domain. The technique first generates a single artificial negative document AN. The sets P and {AN} are then used to build a naï ve Bayesian classifier. Our experiment results show that this method is significantly better than existing techniques.

AIIM Journal 2005 Journal Article

Discovering reliable protein interactions from high-throughput experimental data using network topology

• Jin Chen
• Wynne Hsu
• Mong Li Lee
• See-Kiong Ng

Objective: Current protein–protein interaction (PPI) detection via high-throughput experimental methods, such as yeast-two-hybrid has been reported to be highly erroneous, leading to potentially costly spurious discoveries. This work introduces a novel measure called IRAP, i. e. “interaction reliability by alternative path”, for assessing the reliability of protein interactions based on the underlying topology of the PPI network. Methods and materials: A candidate PPI is considered to be reliable if it is involved in a closed loop in which the alternative path of interactions between the two interacting proteins is strong. We devise an algorithm called AlternativePathFinder to compute the IRAP value for each interaction in a complex PPI network. Validation of the IRAP as a measure for assessing the reliability of PPIs is performed with extensive experiments on yeast PPI data. All the data used in our experiments can be downloaded from our supplementary data web site at http: //www. comp. nus. edu. sg/∼chenjin/data. html. Results: Results show consistently that IRAP measure is an effective way for discovering reliable PPIs in large datasets of error-prone experimentally-derived PPIs. Results also indicate that IRAP is better than IG2, and markedly better than the more simplistic IG1 measure. Conclusion: Experimental results demonstrate that a global, system-wide approach—such as IRAP that considers the entire interaction network instead of merely local neighbors—is a much more promising approach for assessing the reliability of PPIs.

SODA Conference 2000 Conference Paper

Fast practical solution of sorting by reversals

• Alberto Caprara
• Giuseppe Lancia
• See-Kiong Ng