More Like this

1. Scaffolding a Student to Instill Knowledge

   Anil Kag, Durmus Alp (May 2023, International Conference on Learning Representations)

   We propose a novel knowledge distillation (KD) method to selectively instill teacher knowledge into a student model motivated by situations where the student’s capacity is significantly smaller than that of the teachers. In vanilla KD, the teacher primarily sets a predictive target for the student to follow, and we posit that this target is overly optimistic due to the student’s lack of capacity. We develop a novel scaffolding scheme where the teacher, in addition to setting a predictive target, also scaffolds the student’s prediction by censoring hard-to-learn examples. The student model utilizes the same information as the teacher’s soft-max predictions as inputs, and in this sense, our proposal can be viewed as a natural variant of vanilla KD. We show on synthetic examples that censoring hard-examples leads to smoothening the student’s loss landscape so that the student encounters fewer local minima. As a result, it has good generalization properties. Against vanilla KD, we achieve improved performance and are comparable to more intrusive techniques that leverage feature matching on benchmark datasets. 

   more » « less
2. RELIANT: Fair Knowledge Distillation for Graph Neural Networks

   Dong, Yushun; Zhang, Binchi; Yuan, Yiling; Zou, Na; Wang, Qi; Li, Jundong (January 2023, Proceedings of the 2023 SIAM International Conference on Data Mining)

   Graph Neural Networks (GNNs) have shown satisfying performance on various graph learning tasks. To achieve better fitting capability, most GNNs are with a large number of parameters, which makes these GNNs computationally expensive. Therefore, it is difficult to deploy them onto edge devices with scarce computational resources, e.g., mobile phones and wearable smart devices. Knowledge Distillation (KD) is a common solution to compress GNNs, where a light-weighted model (i.e., the student model) is encouraged to mimic the behavior of a computationally expensive GNN (i.e., the teacher GNN model). Nevertheless, most existing GNN-based KD methods lack fairness consideration. As a consequence, the student model usually inherits and even exaggerates the bias from the teacher GNN. To handle such a problem, we take initial steps towards fair knowledge distillation for GNNs. Specifically, we first formulate a novel problem of fair knowledge distillation for GNN-based teacher-student frameworks. Then we propose a principled framework named RELIANT to mitigate the bias exhibited by the student model. Notably the design of RELIANT is decoupled from any specific teacher and student model structures, and thus can be easily adapted to various GNN-based KD frameworks. We perform extensive experiments on multiple real-world datasets, which corroborates that RELIANT achieves less biased GNN knowledge distillation while maintaining high prediction utility. Open-source code can be found at https://github.com/yushundong/RELIANT. 

   more » « less
3. Undistillable: Making A Nasty Teacher That CANNOT teach students

   Haoyu Ma, Tianlong Chen (May 2021, International Conference on Learning Representations ICLR 2021)

   null (Ed.)

   Knowledge Distillation (KD) is a widely used technique to transfer knowledge from pre-trained teacher models to (usually more lightweight) student models. However, in certain situations, this technique is more of a curse than a blessing. For instance, KD poses a potential risk of exposing intellectual properties (IPs): even if a trained machine learning model is released in ``black boxes'' (e.g., as executable software or APIs without open-sourcing code), it can still be replicated by KD through imitating input-output behaviors. To prevent this unwanted effect of KD, this paper introduces and investigates a concept called : a specially trained teacher network that yields nearly the same performance as a normal one, but would significantly degrade the performance of student models learned by imitating it. We propose a simple yet effective algorithm to build the nasty teacher, called . Specifically, we aim to maximize the difference between the output of the nasty teacher and a normal pre-trained network. Extensive experiments on several datasets demonstrate that our method is effective on both standard KD and data-free KD, providing the desirable KD-immunity to model owners for the first time. We hope our preliminary study can draw more awareness and interest in this new practical problem of both social and legal importance. Our codes and pre-trained models can be found at: $$\url{https://github.com/VITA-Group/Nasty-Teacher}$$. 

   more » « less
4. No Head Left Behind - Multi-Head Alignment Distillation for Transformers

   Zhao, T; Singh, K Y; Appalaraju, S; Tang, P; Mahadevan, V; Manmatha, R; Wu, Y N (February 2024, AAAI Conference on Artificial Intelligence)

   Knowledge distillation aims at reducing model size without compromising much performance. Recent work has applied it to large vision-language (VL) Transformers, and has shown that attention maps in the multi-head attention modules of vision-language Transformers contain extensive intra-modal and cross-modal co-reference relations to be distilled. The standard approach is to apply a one-to-one attention map distillation loss, i.e. the Teacher’s first attention head instructs the Student’s first head, the second teaches the second, and so forth, but this only works when the numbers of attention heads in the Teacher and Student are the same. To remove this constraint, we propose a new Attention Map Alignment Distillation (AMAD) method for Transformers with multi-head attention, which works for a Teacher and a Student with different numbers of attention heads. Specifically, we soft-align different heads in Teacher and Student attention maps using a cosine similarity weighting. The Teacher head contributes more to the Student heads for which it has a higher similarity weight. Each Teacher head contributes to all the Student heads by minimizing the divergence between the attention activation distributions for the soft-aligned heads. No head is left behind. This distillation approach operates like cross-attention. We experiment on distilling VL-T5 and BLIP, and apply AMAD loss on their T5, BERT, and ViT sub-modules. We show, under vision-language setting, that AMAD outperforms conventional distillation methods on VQA-2.0, COCO captioning, and Multi30K translation datasets. We further show that even without VL pre-training, the distilled VL-T5 models outperform corresponding VL pre-trained VL-T5 models that are further fine-tuned by ground-truth signals, and that fine-tuning distillation can also compensate to some degree for the absence of VL pre-training for BLIP models. 

   more » « less
5. Revisiting Data-Free Knowledge Distillation with Poisoned Teachers

   Hong, Junyuan; Zeng, Yi; Yu, Shuyang; Lyu, Lingjuan; Jia, Ruoxi; Zhou, Jiayu (July 2023, Proceedings of the 40th International Conference on Machine Learning)

   Data-free knowledge distillation (KD) helps transfer knowledge from a pre-trained model (known as the teacher model) to a smaller model (known as the student model) without access to the original training data used for training the teacher model. However, the security of the synthetic or out-of-distribution (OOD) data required in data-free KD is largely unknown and under-explored. In this work, we make the first effort to uncover the security risk of data-free KD w.r.t. untrusted pre-trained models. We then propose Anti-Backdoor Data-Free KD (ABD), the first plug-in defensive method for data-free KD methods to mitigate the chance of potential backdoors being transferred. We empirically evaluate the effectiveness of our proposed ABD in diminishing transferred backdoor knowledge while maintaining compatible downstream performances as the vanilla KD. We envision this work as a milestone for alarming and mitigating the potential backdoors in data-free KD. Codes are released at https://github.com/illidanlab/ABD . 

   more » « less