Author name cluster

Sinno Pan

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

15 papers

1 author row

NeurIPS Conference 2025 Conference Paper

GLID$^2$E: A Gradient-Free Lightweight Fine-tune Approach for Discrete Biological Sequence Design

Hanqun Cao
Haosen Shi
Chenyu Wang
Sinno Pan
Pheng-Ann Heng

The design of biological sequences is essential for engineering functional biomolecules that contribute to advancements in human health and biotechnology. Recent advances in diffusion models, with their generative power and efficient conditional sampling, have made them a promising approach for sequence generation. To enhance model performance on limited data and enable multi-objective design and optimization, reinforcement learning (RL)-based fine-tuning has shown great potential. However, existing post-sampling and fine-tuning methods either lack stability in discrete optimization when avoiding gradients or incur high computational costs when employing gradient-based approaches, creating significant challenges for achieving both control and stability in the tuning process. To address these limitations, we propose GLID$^2$E, a gradient-free RL-based tuning approach for discrete diffusion models. Our method introduces a clipped likelihood constraint to regulate the exploration space and implements reward shaping to better align the generative process with design objectives, ensuring a more stable and efficient tuning process. By integrating these techniques, GLID$^2$E mitigates training instabilities commonly encountered in RL and diffusion-based frameworks, enabling robust optimization even in challenging biological design tasks. In the DNA sequence and protein sequence design systems, GLID$^2$E achieves competitive performance in function-based design while maintaining computational efficiency and a flexible tuning mechanism.

NeurIPS Conference 2025 Conference Paper

MetaDefense: Defending Fine-tuning based Jailbreak Attack Before and During Generation

Weisen Jiang
Sinno Pan

This paper introduces MetaDefense, a novel framework for defending against finetuning-based jailbreak attacks in large language models (LLMs). We observe that existing defense mechanisms fail to generalize to harmful queries disguised by unseen attack templates, despite LLMs being capable of distinguishing disguised harmful queries in the embedding space. Based on these insights, we propose a two-stage defense approach: (i) pre-generation defense that detects harmful queries before response generation begins, and (ii) mid-generation defense that monitors partial responses during generation to prevent outputting more harmful content. Our MetaDefense trains the LLM to predict the harmfulness of both queries and partial responses using specialized prompts, enabling early termination of potentially harmful interactions. Extensive experiments across multiple LLM architectures (LLaMA-2-7B, Qwen-2. 5-3B-Instruct, and LLaMA-3. 2-3B-Instruct) demonstrate that MetaDefense significantly outperforms existing defense mechanisms, achieving robust defense against harmful queries with seen and unseen attack templates while maintaining competitive performance on benign tasks. Code is available at https: //github. com/ws-jiang/MetaDefense.

NeurIPS Conference 2023 Conference Paper

Retaining Beneficial Information from Detrimental Data for Neural Network Repair

Long-Kai Huang
Peilin Zhao
Junzhou Huang
Sinno Pan

The performance of deep learning models heavily relies on the quality of the training data. Inadequacies in the training data, such as corrupt input or noisy labels, can lead to the failure of model generalization. Recent studies propose repairing the model by identifying the training samples that contribute to the failure and removing their influence from the model. However, it is important to note that the identified data may contain both beneficial and detrimental information. Simply erasing the information of the identified data from the model can have a negative impact on its performance, especially when accurate data is mistakenly identified as detrimental and removed. To overcome this challenge, we propose a novel approach that leverages the knowledge obtained from a retained clean set. Our method first identifies harmful data by utilizing the clean set, then separates the beneficial and detrimental information within the identified data. Finally, we utilize the extracted beneficial information to enhance the model's performance. Through empirical evaluations, we demonstrate that our method outperforms baseline approaches in both identifying harmful data and rectifying model failures. Particularly in scenarios where identification is challenging and a significant amount of benign data is involved, our method improves performance while the baselines deteriorate due to the erroneous removal of beneficial information.

NeurIPS Conference 2022 Conference Paper

Learning Representations via a Robust Behavioral Metric for Deep Reinforcement Learning

Jianda Chen
Sinno Pan

Learning an informative representation with behavioral metrics is able to accelerate the deep reinforcement learning process. There are two key research issues on behavioral metric-based representation learning: 1) how to relax the computation of a specific behavioral metric, which is difficult or even intractable to compute, and 2) how to approximate the relaxed metric by learning an embedding space for states. In this paper, we analyze the potential relaxation and/or approximation gaps for existing behavioral metric-based representation learning methods. Based on the analysis, we propose a new behavioral distance, the RAP distance, and develop a practical representation learning algorithm on top of it with a theoretical analysis. We conduct extensive experiments on DeepMind Control Suite with distraction, Robosuite, and autonomous driving simulator CARLA to demonstrate new state-of-the-art results.

AAAI Conference 2020 Conference Paper

Transfer Value Iteration Networks

Junyi Shen
Hankz Hankui Zhuo
Jin Xu
Bin Zhong
Sinno Pan

Value iteration networks (VINs) have been demonstrated to have a good generalization ability for reinforcement learning tasks across similar domains. However, based on our experiments, a policy learned by VINs still fail to generalize well on the domain whose action space and feature space are not identical to those in the domain where it is trained. In this paper, we propose a transfer learning approach on top of VINs, termed Transfer VINs (TVINs), such that a learned policy from a source domain can be generalized to a target domain with only limited training data, even if the source domain and the target domain have domain-speciﬁc actions and features. We empirically verify that our proposed TVINs outperform VINs when the source and the target domains have similar but not identical action and feature spaces. Furthermore, we show that the performance improvement is consistent across different environments, maze sizes, dataset sizes as well as different values of hyperparameters such as number of iteration and kernel size.

AAAI Conference 2018 Conference Paper

Data Poisoning Attacks on Multi-Task Relationship Learning

Mengchen Zhao
Bo An
Yaodong Yu
Sulin Liu
Sinno Pan

Multi-task learning (MTL) is a machine learning paradigm that improves the performance of each task by exploiting useful information contained in multiple related tasks. However, the relatedness of tasks can be exploited by attackers to launch data poisoning attacks, which has been demonstrated a big threat to single-task learning. In this paper, we provide the ﬁrst study on the vulnerability of MTL. Speciﬁcally, we focus on multi-task relationship learning (MTRL) models, a popular subclass of MTL models where task relationships are quantized and are learned directly from training data. We formulate the problem of computing optimal poisoning attacks on MTRL as a bilevel program that is adaptive to arbitrary choice of target tasks and attacking tasks. We propose an ef- ﬁcient algorithm called PATOM for computing optimal attack strategies. PATOM leverages the optimality conditions of the subproblem of MTRL to compute the implicit gradients of the upper level objective function. Experimental results on realworld datasets show that MTRL models are very sensitive to poisoning attacks and the attacker can signiﬁcantly degrade the performance of target tasks, by either directly poisoning the target tasks or indirectly poisoning the related tasks exploiting the task relatedness. We also found that the tasks being attacked are always strongly correlated, which provides a clue for defending against such attacks.

AAAI Conference 2018 Conference Paper

Sensor-Based Activity Recognition via Learning From Distributions

Hangwei Qian
Sinno Pan
Chunyan Miao

Sensor-based activity recognition aims to predict users’ activities from multi-dimensional streams of various sensor readings received from ubiquitous sensors. To use machine learning techniques for sensor-based activity recognition, previous approaches focused on composing a feature vector to represent sensor-reading streams received within a period of various lengths. With the constructed feature vectors, e. g. , using predeﬁned orders of moments in statistics, and their corresponding labels of activities, standard classiﬁcation algorithms can be applied to train a predictive model, which will be used to make predictions online. However, we argue that in this way some important information, e. g. , statistical information captured by higher-order moments, may be discarded when constructing features. Therefore, in this paper, we propose a new method, denoted by SMMAR, based on learning from distributions for sensor-based activity recognition. Speciﬁcally, we consider sensor readings received within a period as a sample, which can be represented by a feature vector of inﬁnite dimensions in a Reproducing Kernel Hilbert Space (RKHS) using kernel embedding techniques. We then train a classiﬁer in the RKHS. To scale-up the proposed method, we further offer an accelerated version by utilizing an explicit feature map instead of using a kernel function. We conduct experiments on four benchmark datasets to verify the effectiveness and scalability of our proposed method.

AAAI Conference 2017 Conference Paper

Distant Domain Transfer Learning

Ben Tan
Yu Zhang
Sinno Pan
Qiang Yang

In this paper, we study a novel transfer learning problem termed Distant Domain Transfer Learning (DDTL). Different from existing transfer learning problems which assume that there is a close relation between the source domain and the target domain, in the DDTL problem, the target domain can be totally different from the source domain. For example, the source domain classiﬁes face images but the target domain distinguishes plane images. Inspired by the cognitive process of human where two seemingly unrelated concepts can be connected by learning intermediate concepts gradually, we propose a Selective Learning Algorithm (SLA) to solve the DDTL problem with supervised autoencoder or supervised convolutional autoencoder as a base model for handling different types of inputs. Intuitively, the SLA algorithm selects usefully unlabeled data gradually from intermediate domains as a bridge to break the large distribution gap for transferring knowledge between two distant domains. Empirical studies on image classiﬁcation problems demonstrate the effectiveness of the proposed algorithm, and on some tasks the improvement in terms of the classiﬁcation accuracy is up to 17% over “non-transfer” methods.

AAAI Conference 2017 Conference Paper

Knowledge Transfer for Deep Reinforcement Learning with Hierarchical Experience Replay

Haiyan Yin
Sinno Pan

The process for transferring knowledge of multiple reinforcement learning policies into a single multi-task policy via distillation technique is known as policy distillation. When policy distillation is under a deep reinforcement learning setting, due to the giant parameter size and the huge state space for each task domain, it requires extensive computational efforts to train the multi-task policy network. In this paper, we propose a new policy distillation architecture for deep reinforcement learning, where we assume that each task uses its taskspeciﬁc high-level convolutional features as the inputs to the multi-task policy network. Furthermore, we propose a new sampling framework termed hierarchical prioritized experience replay to selectively choose experiences from the replay memories of each task domain to perform learning on the network. With the above two attempts, we aim to accelerate the learning of the multi-task policy network while guaranteeing a good performance. We use Atari 2600 games as testing environment to demonstrate the efﬁciency and effectiveness of our proposed solution for policy distillation.

NeurIPS Conference 2017 Conference Paper

Learning to Prune Deep Neural Networks via Layer-wise Optimal Brain Surgeon

Xin Dong
Shangyu Chen
Sinno Pan

How to develop slim and accurate deep neural networks has become crucial for real- world applications, especially for those employed in embedded systems. Though previous work along this research line has shown some promising results, most existing methods either fail to significantly compress a well-trained deep network or require a heavy retraining process for the pruned deep network to re-boost its prediction performance. In this paper, we propose a new layer-wise pruning method for deep neural networks. In our proposed method, parameters of each individual layer are pruned independently based on second order derivatives of a layer-wise error function with respect to the corresponding parameters. We prove that the final prediction performance drop after pruning is bounded by a linear combination of the reconstructed errors caused at each layer. By controlling layer-wise errors properly, one only needs to perform a light retraining process on the pruned network to resume its original prediction performance. We conduct extensive experiments on benchmark datasets to demonstrate the effectiveness of our pruning method compared with several state-of-the-art baseline methods. Codes of our work are released at: https: //github. com/csyhhu/L-OBS.

AAAI Conference 2016 Conference Paper

Transfer Learning for Cross-Language Text Categorization through Active Correspondences Construction

Joey Zhou
Sinno Pan
Ivor Tsang
Shen-Shyang Ho

Most existing heterogeneous transfer learning (HTL) methods for cross-language text classiﬁcation rely on sufﬁcient cross-domain instance correspondences to learn a mapping across heterogeneous feature spaces, and assume that such correspondences are given in advance. However, in practice, correspondences between domains are usually unknown. In this case, extensively manual efforts are required to establish accurate correspondences across multilingual documents based on their content and meta-information. In this paper, we present a general framework to integrate active learning to construct correspondences between heterogeneous domains for HTL, namely HTL through active correspondences construction (HTLA). Based on this framework, we develop a new HTL method. On top of the new HTL method, we further propose a strategy to actively construct correspondences between domains. Extensive experiments are conducted on various multilingual text classiﬁcation tasks to verify the effectiveness of HTLA.

AAAI Conference 2014 Conference Paper

Hybrid Heterogeneous Transfer Learning through Deep Learning

Joey Zhou
Sinno Pan
Ivor Tsang
Yan Yan

Most previous heterogeneous transfer learning methods learn a cross-domain feature mapping between heterogeneous feature spaces based on a few cross-domain instance-correspondences, and these corresponding instances are assumed to be representative in the source and target domains respectively. However, in many realworld scenarios, this assumption may not hold. As a result, the constructed feature mapping may not be precise due to the bias issue of the correspondences in the target or (and) source domain(s). In this case, a classifier trained on the labeled transformed-sourcedomain data may not be useful for the target domain. In this paper, we present a new transfer learning framework called Hybrid Heterogeneous Transfer Learning (HHTL), which allows the corresponding instances across domains to be biased in either the source or target domain. Specifically, we propose a deep learning approach to learn a feature mapping between crossdomain heterogeneous features as well as a better feature representation for mapped data to reduce the bias issue caused by the cross-domain correspondences. Extensive experiments on several multilingual sentiment classification tasks verify the effectiveness of our proposed approach compared with some baseline methods.

AAAI Conference 2014 Conference Paper

Source Free Transfer Learning for Text Classification

Zhongqi Lu
Yin Zhu
Sinno Pan
Evan Xiang
Yujing Wang
Qiang Yang

Transfer learning uses relevant auxiliary data to help the learning task in a target domain where labeled data is usually insufficient to train an accurate model. Given appropriate auxiliary data, researchers have proposed many transfer learning models. How to find such auxiliary data, however, is of little research so far. In this paper, we focus on the problem of auxiliary data retrieval, and propose a transfer learning framework that effectively selects helpful auxiliary data from an open knowledge space (e. g. the World Wide Web). Because there is no need of manually selecting auxiliary data for different target domain tasks, we call our framework Source Free Transfer Learning (SFTL). For each target domain task, SFTL framework iteratively queries for the helpful auxiliary data based on the learned model and then updates the model using the retrieved auxiliary data. We highlight the automatic constructions of queries and the robustness of the SFTL framework. Our experiments on 20NewsGroup dataset and a Google search snippets dataset suggest that the framework is capable of achieving comparable performance to those state-of-the-art methods with dedicated selections of auxiliary data.

AAAI Conference 2013 Conference Paper

Active Transfer Learning for Cross-System Recommendation

Lili Zhao
Sinno Pan
Evan Xiang
Erheng Zhong
Zhongqi Lu
Qiang Yang

Recommender systems, especially the newly launched ones, have to deal with the data-sparsity issue, where little existing rating information is available. Recently, transfer learning has been proposed to address this problem by leveraging the knowledge from related recommender systems where rich collaborative data are available. However, most previous transfer learning models assume that entity-correspondences across different systems are given as input, which means that for any entity (e. g. , a user or an item) in a target system, its corresponding entity in a source system is known. This assumption can hardly be satisfied in real-world scenarios where entity-correspondences across systems are usually unknown, and the cost of identifying them can be expensive. For example, it is extremely difficult to identify whether a user A from Facebook and a user B from Twitter are the same person. In this paper, we propose a framework to construct entity correspondence with limited budget by using active learning to facilitate knowledge transfer across recommender systems. Specifically, for the purpose of maximizing knowledge transfer, we first iteratively select entities in the target system based on our proposed criterion to query their correspondences in the source system. We then plug the actively constructed entity-correspondence mapping into a general transferred collaborative-filtering model to improve recommendation quality. We perform extensive experiments on real world datasets to verify the effectiveness of our proposed framework for this crosssystem recommendation problem.

AAAI Conference 2011 Conference Paper

Heterogeneous Transfer Learning for Image Classification

Yin Zhu
Yuqiang Chen
Zhongqi Lu
Sinno Pan
Gui-Rong Xue
Yong Yu
Qiang Yang

Transfer learning as a new machine learning paradigm has gained increasing attention lately. In situations where the training data in a target domain are not sufﬁcient to learn predictive models effectively, transfer learning leverages auxiliary source data from other related source domains for learning. While most of the existing works in this area only focused on using the source data with the same structure as the target data, in this paper, we push this boundary further by proposing a heterogeneous transfer learning framework for knowledge transfer between text and images. We observe that for a target-domain classiﬁcation problem, some annotated images can be found on many social Web sites, which can serve as a bridge to transfer knowledge from the abundant text documents available over the Web. A key question is how to effectively transfer the knowledge in the source data even though the text can be arbitrarily found. Our solution is to enrich the representation of the target images with semantic concepts extracted from the auxiliary source data through a novel matrix factorization method. By using the latent semantic features generated by the auxiliary data, we are able to build a better integrated image classiﬁer. We empirically demonstrate the effectiveness of our algorithm on the Caltech-256 image dataset.