Search Results for author:
Found 105 papers, 47 papers with code
DD-TIG at SemEval-2022 Task 5: Investigating the Relationships Between Multimodal and Unimodal Information in Misogynous Memes Detection and Classification
This paper describes our submission for task 5 Multimedia Automatic Misogyny Identification (MAMI) at SemEval-2022.
DD-TIG at Constraint@ACL2022: Multimodal Understanding and Reasoning for Role Labeling of Entities in Hateful Memes
The memes serve as an important tool in online communication, whereas some hateful memes endanger cyberspace by attacking certain people or subjects.
EventKE: Event-Enhanced Knowledge Graph Embedding
Relations in most of the traditional knowledge graphs (KGs) only reflect static and factual connections, but fail to represent the dynamic activities and state changes about entities.
PiTe: Pixel-Temporal Alignment for Large Video-Language Model
Fueled by the Large Language Models (LLMs) wave, Large Visual-Language Models (LVLMs) have emerged as a pivotal advancement, bridging the gap between image and text.
Semi-Supervised Reward Modeling via Iterative Self-Training
Reward models (RM) capture the values and preferences of humans and play a central role in Reinforcement Learning with Human Feedback (RLHF) to align pretrained large language models (LLMs).
LibMOON: A Gradient-based MultiObjective OptimizatioN Library in PyTorch
Multiobjective optimization problems (MOPs) are prevalent in machine learning, with applications in multi-task learning, learning under fairness or robustness constraints, etc.
Localize-and-Stitch: Efficient Model Merging via Sparse Task Arithmetic
Our algorithm works in two steps: i) Localization: identify tiny ($1\%$ of the total parameters) localized regions in the finetuned models containing essential skills for the downstream tasks, and ii) Stitching: reintegrate only these essential regions back into the pretrained model for task synergy.
Transforming Location Retrieval at Airbnb: A Journey from Heuristics to Reinforcement Learning
The Airbnb search system grapples with many unique challenges as it continues to evolve.
Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts
The trained RM serves as a proxy for human preferences.
RLHF Workflow: From Reward Modeling to Online RLHF
We present the workflow of Online Iterative Reinforcement Learning from Human Feedback (RLHF) in this technical report, which is widely reported to outperform its offline counterpart by a large margin in the recent large language model (LLM) literature.
Differentially Private Post-Processing for Fair Regression
This paper describes a differentially private post-processing algorithm for learning fair regressors satisfying statistical parity, addressing privacy concerns of machine learning models trained on sensitive data, as well as fairness concerns of their potential to propagate historical biases.
Optimal Group Fair Classifiers from Linear Post-Processing
We propose a post-processing algorithm for fair classification that mitigates model bias under a unified family of group fairness criteria covering statistical parity, equal opportunity, and equalized odds, applicable to multi-class problems and both attribute-aware and attribute-blind settings.
S4: Self-Supervised Sensing Across the Spectrum
We propose S4 a new self-supervised pre-training approach that significantly reduces the requirement for labeled training data by utilizing two new insights: (a) Satellites capture images in different parts of the spectrum such as radio frequencies, and visible frequencies.
CQIL: Inference Latency Optimization with Concurrent Computation of Quasi-Independent Layers
Empirical experiments of the proposed approach on the LLaMA models confirm that Concurrent Computation of Quasi-Independent Layers (CQIL) can reduce latency by up to 48. 3% on LLaMA-33B, while maintaining a close level of performance.
A Codesign of Scheduling and Parallelization for Large Model Training in Heterogeneous Clusters
The exponentially enlarged scheduling space and ever-changing optimal parallelism plan from adaptive parallelism together result in the contradiction between low-overhead and accurate performance data acquisition for efficient cluster scheduling.
Cobra: Extending Mamba to Multi-Modal Large Language Model for Efficient Inference
In recent years, the application of multimodal large language models (MLLM) in various fields has achieved remarkable success.
GeRM: A Generalist Robotic Model with Mixture-of-experts for Quadruped Robot
Multi-task robot learning holds significant importance in tackling diverse and complex scenarios.
Is Mamba Effective for Time Series Forecasting?
For TSF tasks, these characteristics enable Mamba to comprehend hidden patterns as the Transformer and reduce computational overhead compared to the Transformer.
Ranked #55 on
Time Series Forecasting
on ETTh1 (336) Multivariate
Pairwise Alignment Improves Graph Domain Adaptation
Graph-based methods, pivotal for label inference over interconnected objects in many real-world applications, often encounter generalization challenges, if the graph used for model training differs significantly from the graph used for testing.
Arithmetic Control of LLMs for Diverse User Preferences: Directional Preference Alignment with Multi-Objective Rewards
Additionally, DPA models user preferences as directions (i. e., unit vectors) in the reward space to achieve user-dependent preference control.
A survey of recent methods for addressing AI fairness and bias in biomedicine
Such biases can occur before, during, or after the development of AI models, making it critical to understand and address potential biases to enable the accurate and reliable application of AI models in clinical settings.
Enhancing Compositional Generalization via Compositional Feature Alignment
To delve into the CG challenge, we develop CG-Bench, a suite of CG benchmarks derived from existing real-world image datasets, and observe that the prevalent pretraining-finetuning paradigm on foundational models, such as CLIP and DINOv2, struggles with the challenge.
Robust Multi-Task Learning with Excess Risks
To overcome this limitation, we propose Multi-Task Learning with Excess Risks (ExcessMTL), an excess risk-based task balancing method that updates the task weights by their distances to convergence instead.
Unveiling the Unknown: Unleashing the Power of Unknown to Known in Open-Set Source-Free Domain Adaptation
In contrast this paper advocates that exploring unknown classes can better identify known ones and proposes a domain adaptation model to transfer knowledge on known and unknown classes jointly.
QUAR-VLA: Vision-Language-Action Model for Quadruped Robots
Within this framework, a notable challenge lies in aligning fine-grained instructions with visual perception information.
RSG: Fast Learning Adaptive Skills for Quadruped Robots by Skill Graph
Developing robotic intelligent systems that can adapt quickly to unseen wild situations is one of the critical challenges in pursuing autonomous robotics.
Invariant-Feature Subspace Recovery: A New Class of Provable Domain Generalization Algorithms
First, in the binary classification setup of Rosenfeld et al. (2021), we show that our first algorithm, ISR-Mean, can identify the subspace spanned by invariant features from the first-order moments of the class-conditional distributions, and achieve provable domain generalization with $d_s+1$ training environments.
Towards Practical Non-Adversarial Distribution Matching
Distribution matching can be used to learn invariant representations with applications in fairness and robustness.
Gradual Domain Adaptation: Theory and Algorithms
Unsupervised domain adaptation (UDA) adapts a model from a labeled source domain to an unlabeled target domain in a one-off way.
An Empirical Study of Self-supervised Learning with Wasserstein Distance
We find that the model performance depends on the combination of TWD and probability model, and that the Jeffrey divergence regularization helps in model training.
Learning Multiplex Representations on Text-Attributed Graphs with One Language Model Encoder
Mainstream text representation learning methods use pretrained language models (PLMs) to generate one embedding for each text unit, expecting that all types of relations between texts can be captured by these single-view embeddings.
SC2GAN: Rethinking Entanglement by Self-correcting Correlated GAN Space
We propose a novel framework SC$^2$GAN that achieves disentanglement by re-projecting low-density latent code samples in the original latent space and correcting the editing directions based on both the high-density and low-density regions.
Mitigating the Alignment Tax of RLHF
Building on the analysis and the observation that averaging different layers of the transformer leads to significantly different reward-tax trade-offs, we propose Adaptive Model Averaging (AMA) to adaptively find various combination ratios of model layers.
FFB: A Fair Fairness Benchmark for In-Processing Group Fairness Methods
This paper introduces the Fair Fairness Benchmark (\textsf{FFB}), a benchmarking framework for in-processing group fairness methods.
Structural Re-weighting Improves Graph Domain Adaptation
This work examines different impacts of distribution shifts caused by either graph structure or node attributes and identifies a new type of shift, named conditional structure shift (CSS), which current GDA approaches are provably sub-optimal to deal with.
Explaining Emergent In-Context Learning as Kernel Regression
Then, we empirically investigate the in-context behaviors of language models.
Train Your Own GNN Teacher: Graph-Aware Distillation on Textual Graphs
Different from conventional knowledge distillation, GRAD jointly optimizes a GNN teacher and a graph-free student over the graph's nodes via a shared LM.
Understanding and Constructing Latent Modality Structures in Multi-modal Representation Learning
Hence we advocate that the key of better performance lies in meaningful latent modality structures instead of perfect modality alignment.
Dual-View Selective Instance Segmentation Network for Unstained Live Adherent Cells in Differential Interference Contrast Images
In this study, we developed a novel deep-learning algorithm called dual-view selective instance segmentation network (DVSISN) for segmenting unstained adherent cells in differential interference contrast (DIC) images.
Understanding the Impact of Adversarial Robustness on Accuracy Disparity
More specifically, we demonstrate that while the constraint of adversarial robustness consistently degrades the standard accuracy in the balanced class setting, the class imbalance ratio plays a fundamentally different role in accuracy disparity compared to the Gaussian case, due to the heavy tail of the stable distribution.
Fair and Optimal Classification via Post-Processing
To mitigate the bias exhibited by machine learning models, fairness criteria can be integrated into the training process to ensure fair treatment across all demographics, but it often comes at the expense of model performance.
Greedy Modality Selection via Approximate Submodular Maximization
We formulate a theoretical framework for optimizing modality selection in multimodal learning and introduce a utility measure to quantify the benefit of selecting a modality.
Dense-TNT: Efficient Vehicle Type Classification Neural Network Using Satellite Imagery
Accurate vehicle type classification serves a significant role in the intelligent transportation system.
A SUMO Framework for Deep Reinforcement Learning Experiments Solving Electric Vehicle Charging Dispatching Problem
To better serve further research on various related Deep Reinforcment Learning (DRL) EV dispatching algorithms, an efficient simulation environment is necessary to ensure success.
Exploring Gradient-based Multi-directional Controls in GANs
Generative Adversarial Networks (GANs) have been widely applied in modeling diverse image distributions.
Application of Data Encryption in Chinese Named Entity Recognition
Recently, with the continuous development of deep learning, the performance of named entity recognition tasks has been dramatically improved.
Chinese Named Entity Recognition
named-entity-recognition
+1
FOCUS: Fairness via Agent-Awareness for Federated Learning on Heterogeneous Data
However, due to the heterogeneous nature of local data, it is challenging to optimize or even define fairness of the trained global model for the agents.
Conditional Supervised Contrastive Learning for Fair Text Classification
Contrastive representation learning has gained much attention due to its superior performance in learning representations from both image and sequential data.
Algorithms and Theory for Supervised Gradual Domain Adaptation
We thus study the problem of supervised gradual domain adaptation, where labeled data from shifting distributions are available to the learner along the trajectory, and we aim to learn a classifier on a target data distribution of interest.
Understanding Gradual Domain Adaptation: Improved Analysis, Optimal Path and Beyond
Gradual domain adaptation (GDA), on the other hand, assumes a path of $(T-1)$ unlabeled intermediate domains bridging the source and target, and aims to provide better generalization in the target domain by leveraging the intermediate ones.
Rethinking Task Sampling for Few-shot Vision-Language Transfer Learning
While much literature has been devoted to exploring alternative optimization strategies, we identify another essential aspect towards effective few-shot transfer learning, task sampling, which is previously only be viewed as part of data pre-processing in MAML.
Conditional Contrastive Learning with Kernel
Conditional contrastive learning frameworks consider the conditional sampling procedure that constructs positive or negative data pairs conditioned on specific variables.
Provable Domain Generalization via Invariant-Feature Subspace Recovery
Our first algorithm, ISR-Mean, can identify the subspace spanned by invariant features from the first-order moments of the class-conditional distributions, and achieve provable domain generalization with $d_s+1$ training environments under the data model of Rosenfeld et al. (2021).
Rethinking Controllable Variational Autoencoders
It has shown success in a variety of applications, such as image generation, disentangled representation learning, and language modeling.
Model-free Nearly Optimal Control of Constrained-Input Nonlinear Systems Based on Synchronous Reinforcement Learning
In this paper a novel model-free algorithm is proposed.
Towards Return Parity in Markov Decision Processes
We first provide a decomposition theorem for return disparity, which decomposes the return disparity of any two MDPs sharing the same state and action spaces into the distance between group-wise reward functions, the discrepancy of group policies, and the discrepancy between state visitation distributions induced by the group policies.
A Nearly Optimal Chattering Reduction Method of Sliding Mode Control With an Application to a Two-wheeled Mobile Robot
First, the deficiency of chattering in traditional SMC and the quasi-SMC method are analyzed in this paper.
FedMM: Saddle Point Optimization for Federated Adversarial Domain Adaptation
Federated adversary domain adaptation is a unique distributed minimax training task due to the prevalence of label imbalance among clients, with each client only seeing a subset of the classes of labels required to train a global model.
Learning Invariant Representations on Multilingual Language Models for Unsupervised Cross-Lingual Transfer
Recent advances in neural modeling have produced deep multilingual language models capable of extracting cross-lingual knowledge from unparallel texts, as evidenced by their decent zero-shot transfer performance.
Robust and Personalized Federated Learning with Spurious Features: an Adversarial Approach
To this end, we propose a strategy to mitigate the effect of spurious features based on our observation that the global model in the federated learning step has a low accuracy disparity due to statistical heterogeneity.
Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptation
Despite the subtle difference between MTL and meta-learning in the problem formulation, both learning paradigms share the same insight that the shared structure between existing training tasks could lead to better generalization and adaptation.
Ranked #17 on
Few-Shot Image Classification
on FC100 5-way (1-shot)
Invariant Information Bottleneck for Domain Generalization
IIB significantly outperforms IRM on synthetic datasets, where the pseudo-invariant features and geometric skews occur, showing the effectiveness of proposed formulation in overcoming failure modes of IRM.
Online Continual Adaptation with Active Self-Training
Our theoretical results show that OSAMD can fast adapt to changing environments with active queries.
Quantifying and Improving Transferability in Domain Generalization
We then prove that our transferability can be estimated with enough samples and give a new upper bound for the target error based on our transferability.
Conditional Contrastive Learning for Improving Fairness in Self-Supervised Learning
In this paper, we propose a Conditional Contrastive Learning (CCL) approach to improve the fairness of contrastive SSL methods.
Online Adaptive Optimal Control Algorithm Based on Synchronous Integral Reinforcement Learning With Explorations
In this paper, we present a novel algorithm named synchronous integral Q-learning, which is based on synchronous policy iteration, to solve the continuous-time infinite horizon optimal control problems of input-affine system dynamics.
Adaptive Fractional-Order Sliding Mode Controller with Neural Network Compensator for an Ultrasonic Motor
Ultrasonic motors (USMs) are commonly used in aerospace, robotics, and medical devices, where fast and precise motion is needed.
Self-supervised Representation Learning with Relative Predictive Coding
This paper introduces Relative Predictive Coding (RPC), a new contrastive representation learning objective that maintains a good balance among training stability, minibatch size sensitivity, and downstream task performance.
Understanding and Mitigating Accuracy Disparity in Regression
With the widespread deployment of large-scale prediction systems in high-stakes domains, e. g., face recognition, criminal justice, etc., disparity in prediction accuracy between different demographic subgroups has called for fundamental understanding on the source of such disparity and algorithmic intervention to mitigate it.
Acoustic Structure Inverse Design and Optimization Using Deep Learning
From ancient to modern times, acoustic structures have been used to control the propagation of acoustic waves.
On Dyadic Fairness: Exploring and Mitigating Bias in Graph Connections
Disparate impact has raised serious concerns in machine learning applications and its societal impacts.
Fundamental Limits and Tradeoffs in Invariant Representation Learning
A wide range of machine learning applications such as privacy-preserving learning, algorithmic fairness, and domain adaptation/generalization among others, involve learning invariant representations of the data that aim to achieve two competing goals: (a) maximize information or accuracy with respect to a target response, and (b) maximize invariance or independence with respect to a set of protected features (e. g., for fairness, privacy, etc).
Model-based Policy Optimization with Unsupervised Model Adaptation
However, due to the potential distribution mismatch between simulated data and real data, this could lead to degraded performance.
Learning Invariant Representations and Risks for Semi-supervised Domain Adaptation
First, we provide a finite sample bound for both classification and regression problems under Semi-DA.
Information Obfuscation of Graph Neural Networks
While the advent of Graph Neural Networks (GNNs) has greatly improved node and graph representation learning in many applications, the neighborhood aggregation scheme exposes additional vulnerabilities to adversaries seeking to extract node-level information about sensitive attributes.
DynamicVAE: Decoupling Reconstruction Error and Disentangled Representation Learning
Existing methods, such as $\beta$-VAE and FactorVAE, assign a large weight to the KL-divergence term in the objective function, leading to high reconstruction errors for the sake of better disentanglement.
A Review of Single-Source Deep Unsupervised Visual Domain Adaptation
To cope with limited labeled training data, many have attempted to directly apply models trained on a large-scale labeled source domain to another sparsely labeled or unlabeled target domain.
On Learning Language-Invariant Representations for Universal Machine Translation
The goal of universal machine translation is to learn to translate between any pair of languages, given a corpus of paired translated documents for \emph{a small subset} of all pairs of languages.
Neural Methods for Point-wise Dependency Estimation
Since its inception, the neural estimation of mutual information (MI) has demonstrated the empirical success of modeling expected dependency between high-dimensional random variables.
Domain Adaptation with Conditional Distribution Matching and Generalized Label Shift
However, recent work has shown limitations of this approach when label distributions differ between the source and target domains.
Continual Learning with Adaptive Weights (CLAW)
Approaches to continual learning aim to successfully learn a set of related tasks that arrive in an online manner.
Conditional Learning of Fair Representations
We propose a novel algorithm for learning fair representations that can simultaneously mitigate two notions of disparity among different demographic subgroups in the classification setting.
Adversarial Privacy Preservation under Attribute Inference Attack
With the prevalence of machine learning services, crowdsourced data containing sensitive information poses substantial privacy challenges.
Learning Neural Networks with Adaptive Regularization
Feed-forward neural networks can be understood as a combination of an intermediate representation and a linear hypothesis.
Inherent Tradeoffs in Learning Fair Representations
On the upside, we prove that if the group-wise Bayes optimal classifiers are close, then learning fair representations leads to an alternative notion of fairness, known as the accuracy parity, which states that the error rates are close between groups.
Trade-offs and Guarantees of Adversarial Representation Learning for Information Obfuscation
Meanwhile, it is clear that in general there is a tension between minimizing information leakage and maximizing task accuracy.
Learning From the Experience of Others: Approximate Empirical Bayes in Neural Networks
Learning deep neural networks could be understood as the combination of representation learning and learning halfspaces.
On Learning Invariant Representation for Domain Adaptation
Our result characterizes a fundamental tradeoff between learning invariant representations and achieving small joint error on both domains when the marginal label distributions differ from source to target.
Adversarial Multiple Source Domain Adaptation
In this paper we propose new generalization bounds and algorithms under both classification and regression settings for unsupervised multiple source domain adaptation.
Ranked #3 on
Domain Adaptation
on GTA5+Synscapes to Cityscapes
On Strategyproof Conference Peer Review
We then empirically show that the requisite property on the authorship graph is indeed satisfied in the submission data from the ICLR conference, and further demonstrate a simple trick to make the partitioning method more practically appealing for conference peer review.
Convolutional-Recurrent Neural Networks for Speech Enhancement
By incorporating prior knowledge of speech signals into the design of model structures, we build a model that is more data-efficient and achieves better generalization on both seen and unseen noise.
Active Learning of Strict Partial Orders: A Case Study on Concept Prerequisite Relations
Strict partial order is a mathematical structure commonly seen in relational data.
Discovering Order in Unordered Datasets: Generative Markov Networks
The assumption that data samples are independently identically distributed is the backbone of many learning algorithms.
Multiple Source Domain Adaptation with Adversarial Learning
We propose a new generalization bound for domain adaptation when there are multiple source domains with labeled instances and one target domain with unlabeled instances.
Learning Markov Chain in Unordered Dataset
In this technical report, we introduce OrderNet that can be used to extract the order of data instances in an unsupervised way.
Frank-Wolfe Optimization for Symmetric-NMF under Simplicial Constraint
Symmetric nonnegative matrix factorization has found abundant applications in various domains by providing a symmetric low-rank decomposition of nonnegative matrices.
Multiple Source Domain Adaptation with Adversarial Training of Neural Networks
As a step toward bridging the gap, we propose a new generalization bound for domain adaptation when there are multiple source domains with labeled instances and one target domain with unlabeled instances.
Principled Hybrids of Generative and Discriminative Domain Adaptation
This provides us a very general way to interpolate between generative and discriminative extremes through different choices of priors.
Linear Time Computation of Moments in Sum-Product Networks
We propose a dynamic programming method to further reduce the computation of the moments of all the edges in the graph from quadratic to linear.
Efficient Multitask Feature and Relationship Learning
In this paper, we consider a formulation of multitask learning that learns the relationships both between tasks and between features, represented through a task covariance and a feature covariance matrix, respectively.
A Unified Approach for Learning the Parameters of Sum-Product Networks
We present a unified approach for learning the parameters of Sum-Product networks (SPNs).
Self-Adaptive Hierarchical Sentence Model
The ability to accurately model a sentence at varying stages (e. g., word-phrase-sentence) plays a central role in natural language processing.
Ranked #5 on
Subjectivity Analysis
on SUBJ
On the Relationship between Sum-Product Networks and Bayesian Networks
We conclude the paper with some discussion of the implications of the proof and establish a connection between the depth of an SPN and a lower bound of the tree-width of its corresponding BN.
A Sober Look at Spectral Learning
In contrast, maximum likelihood estimates may get trapped in local optima due to the non-convex nature of the likelihood function of latent variable models.
