Diffusion fashions have not too long ago emerged because the de facto commonplace for producing advanced, high-dimensional outputs. You could know them for his or her capacity to supply gorgeous AI artwork and hyper-realistic artificial photographs, however they’ve additionally discovered success in different functions equivalent to drug design and steady management. The important thing thought behind diffusion fashions is to iteratively rework random noise right into a pattern, equivalent to a picture or protein construction. That is usually motivated as a most chance estimation drawback, the place the mannequin is educated to generate samples that match the coaching information as carefully as doable.
Nevertheless, most use circumstances of diffusion fashions are usually not straight involved with matching the coaching information, however as a substitute with a downstream goal. We don’t simply need a picture that appears like current photographs, however one which has a selected kind of look; we don’t simply desire a drug molecule that’s bodily believable, however one that’s as efficient as doable. On this submit, we present how diffusion fashions could be educated on these downstream targets straight utilizing reinforcement studying (RL). To do that, we finetune Steady Diffusion on quite a lot of targets, together with picture compressibility, human-perceived aesthetic high quality, and prompt-image alignment. The final of those targets makes use of suggestions from a big vision-language mannequin to enhance the mannequin’s efficiency on uncommon prompts, demonstrating how highly effective AI fashions can be utilized to enhance one another with none people within the loop.
A diagram illustrating the prompt-image alignment goal. It makes use of LLaVA, a big vision-language mannequin, to judge generated photographs.
Denoising Diffusion Coverage Optimization
When turning diffusion into an RL drawback, we make solely probably the most primary assumption: given a pattern (e.g. a picture), we now have entry to a reward perform that we will consider to inform us how “good” that pattern is. Our aim is for the diffusion mannequin to generate samples that maximize this reward perform.
Diffusion fashions are usually educated utilizing a loss perform derived from most chance estimation (MLE), that means they’re inspired to generate samples that make the coaching information look extra doubtless. Within the RL setting, we not have coaching information, solely samples from the diffusion mannequin and their related rewards. A technique we will nonetheless use the identical MLE-motivated loss perform is by treating the samples as coaching information and incorporating the rewards by weighting the loss for every pattern by its reward. This provides us an algorithm that we name reward-weighted regression (RWR), after current algorithms from RL literature.
Nevertheless, there are a couple of issues with this method. One is that RWR will not be a very actual algorithm — it maximizes the reward solely roughly (see Nair et. al., Appendix A). The MLE-inspired loss for diffusion can also be not actual and is as a substitute derived utilizing a variational sure on the true chance of every pattern. Because of this RWR maximizes the reward via two ranges of approximation, which we discover considerably hurts its efficiency.
We consider two variants of DDPO and two variants of RWR on three reward features and discover that DDPO persistently achieves the perfect efficiency.
The important thing perception of our algorithm, which we name denoising diffusion coverage optimization (DDPO), is that we will higher maximize the reward of the ultimate pattern if we take note of your complete sequence of denoising steps that obtained us there. To do that, we reframe the diffusion course of as a multi-step Markov determination course of (MDP). In MDP terminology: every denoising step is an motion, and the agent solely will get a reward on the ultimate step of every denoising trajectory when the ultimate pattern is produced. This framework permits us to use many highly effective algorithms from RL literature which are designed particularly for multi-step MDPs. As an alternative of utilizing the approximate chance of the ultimate pattern, these algorithms use the precise chance of every denoising step, which is extraordinarily simple to compute.
We selected to use coverage gradient algorithms on account of their ease of implementation and previous success in language mannequin finetuning. This led to 2 variants of DDPO: DDPOSF, which makes use of the easy rating perform estimator of the coverage gradient also referred to as REINFORCE; and DDPOIS, which makes use of a extra highly effective significance sampled estimator. DDPOIS is our best-performing algorithm and its implementation carefully follows that of proximal coverage optimization (PPO).
Finetuning Steady Diffusion Utilizing DDPO
For our foremost outcomes, we finetune Steady Diffusion v1-4 utilizing DDPOIS. Now we have 4 duties, every outlined by a distinct reward perform:
- Compressibility: How simple is the picture to compress utilizing the JPEG algorithm? The reward is the detrimental file measurement of the picture (in kB) when saved as a JPEG.
- Incompressibility: How exhausting is the picture to compress utilizing the JPEG algorithm? The reward is the optimistic file measurement of the picture (in kB) when saved as a JPEG.
- Aesthetic High quality: How aesthetically interesting is the picture to the human eye? The reward is the output of the LAION aesthetic predictor, which is a neural community educated on human preferences.
- Immediate-Picture Alignment: How nicely does the picture signify what was requested for within the immediate? This one is a little more difficult: we feed the picture into LLaVA, ask it to explain the picture, after which compute the similarity between that description and the unique immediate utilizing BERTScore.
Since Steady Diffusion is a text-to-image mannequin, we additionally want to select a set of prompts to provide it throughout finetuning. For the primary three duties, we use easy prompts of the shape “a(n) [animal]”. For prompt-image alignment, we use prompts of the shape “a(n) [animal] [activity]”, the place the actions are “washing dishes”, “enjoying chess”, and “using a motorcycle”. We discovered that Steady Diffusion usually struggled to supply photographs that matched the immediate for these uncommon situations, leaving loads of room for enchancment with RL finetuning.
First, we illustrate the efficiency of DDPO on the easy rewards (compressibility, incompressibility, and aesthetic high quality). All the photographs are generated with the identical random seed. Within the high left quadrant, we illustrate what “vanilla” Steady Diffusion generates for 9 totally different animals; the entire RL-finetuned fashions present a transparent qualitative distinction. Apparently, the aesthetic high quality mannequin (high proper) tends in the direction of minimalist black-and-white line drawings, revealing the sorts of photographs that the LAION aesthetic predictor considers “extra aesthetic”.
Subsequent, we exhibit DDPO on the extra advanced prompt-image alignment job. Right here, we present a number of snapshots from the coaching course of: every collection of three photographs exhibits samples for a similar immediate and random seed over time, with the primary pattern coming from vanilla Steady Diffusion. Apparently, the mannequin shifts in the direction of a extra cartoon-like fashion, which was not intentional. We hypothesize that it’s because animals doing human-like actions usually tend to seem in a cartoon-like fashion within the pretraining information, so the mannequin shifts in the direction of this fashion to extra simply align with the immediate by leveraging what it already is aware of.
Sudden Generalization
Shocking generalization has been discovered to come up when finetuning giant language fashions with RL: for instance, fashions finetuned on instruction-following solely in English usually enhance in different languages. We discover that the identical phenomenon happens with text-to-image diffusion fashions. For instance, our aesthetic high quality mannequin was finetuned utilizing prompts that have been chosen from an inventory of 45 frequent animals. We discover that it generalizes not solely to unseen animals but additionally to on a regular basis objects.
Our prompt-image alignment mannequin used the identical record of 45 frequent animals throughout coaching, and solely three actions. We discover that it generalizes not solely to unseen animals but additionally to unseen actions, and even novel mixtures of the 2.
Overoptimization
It’s well-known that finetuning on a reward perform, particularly a realized one, can result in reward overoptimization the place the mannequin exploits the reward perform to attain a excessive reward in a non-useful method. Our setting is not any exception: in all of the duties, the mannequin finally destroys any significant picture content material to maximise reward.
We additionally found that LLaVA is prone to typographic assaults: when optimizing for alignment with respect to prompts of the shape “[n] animals”, DDPO was in a position to efficiently idiot LLaVA by as a substitute producing textual content loosely resembling the proper quantity.
There’s at the moment no general-purpose methodology for stopping overoptimization, and we spotlight this drawback as an necessary space for future work.
Conclusion
Diffusion fashions are exhausting to beat in the case of producing advanced, high-dimensional outputs. Nevertheless, up to now they’ve largely been profitable in functions the place the aim is to study patterns from heaps and plenty of information (for instance, image-caption pairs). What we’ve discovered is a strategy to successfully prepare diffusion fashions in a method that goes past pattern-matching — and with out essentially requiring any coaching information. The chances are restricted solely by the standard and creativity of your reward perform.
The way in which we used DDPO on this work is impressed by the current successes of language mannequin finetuning. OpenAI’s GPT fashions, like Steady Diffusion, are first educated on enormous quantities of Web information; they’re then finetuned with RL to supply helpful instruments like ChatGPT. Sometimes, their reward perform is realized from human preferences, however others have extra not too long ago discovered the way to produce highly effective chatbots utilizing reward features primarily based on AI suggestions as a substitute. In comparison with the chatbot regime, our experiments are small-scale and restricted in scope. However contemplating the large success of this “pretrain + finetune” paradigm in language modeling, it actually looks like it’s value pursuing additional on the earth of diffusion fashions. We hope that others can construct on our work to enhance giant diffusion fashions, not only for text-to-image era, however for a lot of thrilling functions equivalent to video era, music era, picture enhancing, protein synthesis, robotics, and extra.
Moreover, the “pretrain + finetune” paradigm will not be the one method to make use of DDPO. So long as you’ve gotten a great reward perform, there’s nothing stopping you from coaching with RL from the beginning. Whereas this setting is as-yet unexplored, this can be a place the place the strengths of DDPO might actually shine. Pure RL has lengthy been utilized to all kinds of domains starting from enjoying video games to robotic manipulation to nuclear fusion to chip design. Including the highly effective expressivity of diffusion fashions to the combo has the potential to take current functions of RL to the subsequent stage — and even to find new ones.
This submit relies on the next paper:
If you wish to study extra about DDPO, you may take a look at the paper, web site, authentic code, or get the mannequin weights on Hugging Face. If you wish to use DDPO in your personal undertaking, take a look at my PyTorch + LoRA implementation the place you may finetune Steady Diffusion with lower than 10GB of GPU reminiscence!
If DDPO conjures up your work, please cite it with:
@misc{black2023ddpo,
title={Coaching Diffusion Fashions with Reinforcement Studying},
creator={Kevin Black and Michael Janner and Yilun Du and Ilya Kostrikov and Sergey Levine},
yr={2023},
eprint={2305.13301},
archivePrefix={arXiv},
primaryClass={cs.LG}
}
